inpaintServer/logs/main_server.log

WARNING:root:jtop library not found. Jetson monitoring will be limited. Please run 'sudo pip install jetson-stats'
INFO:     Started server process [16093]
INFO:     Waiting for application startup.
INFO:main:🚀 인페인팅 서버 시작 중...
2025-09-30 14:10:55,233 - main - INFO - 🚀 인페인팅 서버 시작 중...
INFO:main:✅ 공유 객체를 app.state에 저장 완료
2025-09-30 14:10:55,234 - main - INFO - ✅ 공유 객체를 app.state에 저장 완료
INFO:main:🔄 상태 저장 백그라운드 작업 생성 중...
2025-09-30 14:10:55,234 - main - INFO - 🔄 상태 저장 백그라운드 작업 생성 중...
INFO:main:✅ 상태 저장 백그라운드 작업 생성 완료
2025-09-30 14:10:55,234 - main - INFO - ✅ 상태 저장 백그라운드 작업 생성 완료
INFO:main:🚀 세션 풀 초기화 (CUDA 자동 감지)
2025-09-30 14:10:55,234 - main - INFO - 🚀 세션 풀 초기화 (CUDA 자동 감지)
INFO:app.core.session_pool:Initializing dynamic session pools...
2025-09-30 14:10:55,234 - app.core.session_pool - INFO - Initializing dynamic session pools...
INFO:app.core.session_pool:Pre-loading 2 sessions for simple_lama
2025-09-30 14:10:55,234 - app.core.session_pool - INFO - Pre-loading 2 sessions for simple_lama
INFO:main:🔄 상태 저장 백그라운드 작업 시작됨
2025-09-30 14:10:55,234 - main - INFO - 🔄 상태 저장 백그라운드 작업 시작됨
INFO:app.core.session_pool:Creating new session simple_lama_0 for simple_lama...
2025-09-30 14:10:55,235 - app.core.session_pool - INFO - Creating new session simple_lama_0 for simple_lama...
INFO:app.core.session_pool:Creating new session simple_lama_1 for simple_lama...
2025-09-30 14:10:56,821 - app.core.session_pool - INFO - Creating new session simple_lama_1 for simple_lama...
INFO:app.models.simple_lama:Loading Simple LAMA model...
2025-09-30 14:10:56,822 - app.models.simple_lama - INFO - Loading Simple LAMA model...
INFO:app.models.simple_lama:실제 SimpleLama 모델 로딩 완료
2025-09-30 14:10:57,770 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
INFO:app.models.simple_lama:Simple LAMA model loaded successfully
2025-09-30 14:10:57,770 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
INFO:app.models.simple_lama:Loading Simple LAMA model...
2025-09-30 14:10:57,770 - app.models.simple_lama - INFO - Loading Simple LAMA model...
INFO:app.models.simple_lama:실제 SimpleLama 모델 로딩 완료
2025-09-30 14:10:58,493 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
INFO:app.models.simple_lama:Simple LAMA model loaded successfully
2025-09-30 14:10:58,493 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
INFO:app.core.session_pool:Successfully created session simple_lama_0
2025-09-30 14:10:58,493 - app.core.session_pool - INFO - Successfully created session simple_lama_0
INFO:app.core.session_pool:➕ Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (7.3%)
2025-09-30 14:10:58,494 - app.core.session_pool - INFO - ➕ Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (7.3%)
INFO:app.core.session_pool:Successfully created session simple_lama_1
2025-09-30 14:10:58,494 - app.core.session_pool - INFO - Successfully created session simple_lama_1
INFO:app.core.session_pool:➕ Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (7.3%)
2025-09-30 14:10:58,494 - app.core.session_pool - INFO - ➕ Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (7.3%)
INFO:app.core.session_pool:Pre-loading 1 sessions for migan
2025-09-30 14:10:58,494 - app.core.session_pool - INFO - Pre-loading 1 sessions for migan
INFO:app.core.session_pool:Creating new session migan_0 for migan...
2025-09-30 14:10:58,494 - app.core.session_pool - INFO - Creating new session migan_0 for migan...
INFO:app.models.migan:Loading MIGAN ONNX model...
2025-09-30 14:10:58,534 - app.models.migan - INFO - Loading MIGAN ONNX model...
INFO:app.models.migan:MIGAN ONNX 런타임 세션 생성 시도...
2025-09-30 14:10:58,534 - app.models.migan - INFO - MIGAN ONNX 런타임 세션 생성 시도...
INFO:app.models.migan:MIGAN ONNX providers 설정: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-09-30 14:10:58,535 - app.models.migan - INFO - MIGAN ONNX providers 설정: ['CUDAExecutionProvider', 'CPUExecutionProvider']
INFO:app.models.migan:MIGAN ONNX 세션 생성 완료. Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-09-30 14:10:58,804 - app.models.migan - INFO - MIGAN ONNX 세션 생성 완료. Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
INFO:app.models.migan:MIGAN ONNX model loaded successfully
2025-09-30 14:10:58,804 - app.models.migan - INFO - MIGAN ONNX model loaded successfully
INFO:app.core.session_pool:Successfully created session migan_0
2025-09-30 14:10:58,804 - app.core.session_pool - INFO - Successfully created session migan_0
INFO:app.core.session_pool:➕ Session Created (migan). Status -> simple_lama: 2, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (7.7%)
2025-09-30 14:10:58,805 - app.core.session_pool - INFO - ➕ Session Created (migan). Status -> simple_lama: 2, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (7.7%)
INFO:app.core.session_pool:Pre-loading 1 sessions for rembg
2025-09-30 14:10:58,805 - app.core.session_pool - INFO - Pre-loading 1 sessions for rembg
INFO:app.core.session_pool:Creating new session rembg_0 for rembg...
2025-09-30 14:10:58,805 - app.core.session_pool - INFO - Creating new session rembg_0 for rembg...
INFO:app.models.bria_rmbg_onnx:BriaRMBGOnnxProcessor 초기화 완료
2025-09-30 14:10:58,806 - app.models.bria_rmbg_onnx - INFO - BriaRMBGOnnxProcessor 초기화 완료
INFO:app.models.bria_rmbg_onnx:Bria RMBG ONNX 세션 생성 중... path=app/models/onnx/BriaRMBG1.4_model_fp16.onnx
2025-09-30 14:10:58,806 - app.models.bria_rmbg_onnx - INFO - Bria RMBG ONNX 세션 생성 중... path=app/models/onnx/BriaRMBG1.4_model_fp16.onnx
INFO:app.models.bria_rmbg_onnx:Bria RMBG ONNX 세션 생성 완료, Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'] | Input: input, Output: output
2025-09-30 14:10:59,204 - app.models.bria_rmbg_onnx - INFO - Bria RMBG ONNX 세션 생성 완료, Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'] | Input: input, Output: output
INFO:app.core.session_pool:Successfully created session rembg_0
2025-09-30 14:10:59,205 - app.core.session_pool - INFO - Successfully created session rembg_0
INFO:app.core.session_pool:➕ Session Created (rembg). Status -> simple_lama: 2, migan: 1, rembg: 0 | VRAM: 0.0/0.0 GB (8.9%)
2025-09-30 14:10:59,206 - app.core.session_pool - INFO - ➕ Session Created (rembg). Status -> simple_lama: 2, migan: 1, rembg: 0 | VRAM: 0.0/0.0 GB (8.9%)
INFO:app.core.session_pool:Session pools initialized successfully
2025-09-30 14:10:59,206 - app.core.session_pool - INFO - Session pools initialized successfully
INFO:main:✅ 세션 풀 초기화 완료
2025-09-30 14:10:59,206 - main - INFO - ✅ 세션 풀 초기화 완료
INFO:app.core.worker_manager:Starting worker manager...
2025-09-30 14:10:59,206 - app.core.worker_manager - INFO - Starting worker manager...
INFO:app.core.worker_manager:Worker manager started with 2 workers
2025-09-30 14:10:59,207 - app.core.worker_manager - INFO - Worker manager started with 2 workers
INFO:main:✅ 워커 매니저 시작 완료
2025-09-30 14:10:59,207 - main - INFO - ✅ 워커 매니저 시작 완료
INFO:app.core.batch_manager:Starting BatchManager...
2025-09-30 14:10:59,207 - app.core.batch_manager - INFO - Starting BatchManager...
INFO:app.core.batch_manager:BatchManager started successfully.
2025-09-30 14:10:59,207 - app.core.batch_manager - INFO - BatchManager started successfully.
INFO:main:✅ 배치 관리자 시작 완료
2025-09-30 14:10:59,207 - main - INFO - ✅ 배치 관리자 시작 완료
INFO:main:🎉 인페인팅 서버 시작 완료!
2025-09-30 14:10:59,207 - main - INFO - 🎉 인페인팅 서버 시작 완료!
WARNING:app.utils.discord_notifier:Discord 웹훅 URL이 설정되지 않아 알림을 보낼 수 없습니다.
2025-09-30 14:10:59,208 - app.utils.discord_notifier - WARNING - Discord 웹훅 URL이 설정되지 않아 알림을 보낼 수 없습니다.
INFO:app.core.session_pool:Idle session reaper started. Timeout: 1800s, Check Interval: 60s
2025-09-30 14:10:59,209 - app.core.session_pool - INFO - Idle session reaper started. Timeout: 1800s, Check Interval: 60s
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8008 (Press CTRL+C to quit)
INFO:     127.0.0.1:37068 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:37072 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:33456 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:11:40,105 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:11:48,281 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 8.175s
2025-09-30 14:11:48,282 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 8.175s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 8.177s
2025-09-30 14:11:48,282 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 8.177s
INFO:     127.0.0.1:55696 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:     122.35.47.45:53189 - "GET /docs HTTP/1.1" 200 OK
INFO:     127.0.0.1:46326 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:11:48,529 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:11:48,608 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.078s
2025-09-30 14:11:48,608 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.078s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.079s
2025-09-30 14:11:48,608 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.079s
INFO:     127.0.0.1:46340 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:     122.35.47.45:53189 - "GET /openapi.json HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:11:48,861 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:11:48,931 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.070s
2025-09-30 14:11:48,932 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.070s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.071s
2025-09-30 14:11:48,932 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.071s
INFO:     127.0.0.1:46344 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:11:49,126 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:11:49,199 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.072s
2025-09-30 14:11:49,199 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.072s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.073s
2025-09-30 14:11:49,200 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.073s
INFO:     127.0.0.1:46360 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:11:49,388 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:11:49,459 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.070s
2025-09-30 14:11:49,459 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.070s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.071s
2025-09-30 14:11:49,460 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.071s
INFO:     127.0.0.1:46370 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:     127.0.0.1:46378 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46384 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46394 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59326 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59334 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59336 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59350 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59356 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59366 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:59378 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55178 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:12:04,282 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:12:04,361 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.079s
2025-09-30 14:12:04,362 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.079s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.080s
2025-09-30 14:12:04,362 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.080s
INFO:     127.0.0.1:55190 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:12:04,602 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:12:04,676 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.072s
2025-09-30 14:12:04,676 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.072s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.074s
2025-09-30 14:12:04,676 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.074s
INFO:     127.0.0.1:55202 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:12:04,878 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:12:04,947 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.068s
2025-09-30 14:12:04,948 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.068s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.070s
2025-09-30 14:12:04,948 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.070s
INFO:     127.0.0.1:55216 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:     127.0.0.1:55222 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:12:05,136 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:12:05,213 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.076s
2025-09-30 14:12:05,213 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.076s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.077s
2025-09-30 14:12:05,213 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.077s
INFO:     127.0.0.1:55224 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:12:05,407 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=113.244
2025-09-30 14:12:05,478 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=113.244
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.071s
2025-09-30 14:12:05,478 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.071s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.072s
2025-09-30 14:12:05,479 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.072s
INFO:     127.0.0.1:55238 - "POST /api/v1/remove_bg?response_format=base64&image_format=png HTTP/1.1" 200 OK
INFO:     127.0.0.1:55246 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55258 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55268 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55272 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55280 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47214 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47216 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47220 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47230 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47240 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47254 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60540 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60550 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60556 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60570 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60574 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60582 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60584 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:52622 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52624 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52638 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52640 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52646 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52658 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52666 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45198 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45212 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45214 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45222 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45232 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45238 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37744 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37750 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37752 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37764 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37772 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45948 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45962 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:45968 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45978 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45990 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45994 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46010 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59452 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59458 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59462 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59468 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59470 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59482 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53000 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53008 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53014 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53016 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53018 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53026 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44244 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44252 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:44258 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44270 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44272 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44278 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44286 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44288 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50528 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50530 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50538 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50544 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50550 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37300 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37314 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37318 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37332 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37340 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37356 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37366 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54616 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54628 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:54642 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54656 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54668 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54678 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54690 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40218 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40220 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40228 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40236 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40252 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40260 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53372 - "GET /health HTTP/1.1" 404 Not Found
INFO:     127.0.0.1:40262 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46724 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46732 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46738 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46740 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46744 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46746 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46754 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47814 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47818 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:47822 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47832 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47846 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47856 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47858 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56892 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56902 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56914 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56922 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56926 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56936 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56940 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44362 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44378 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44380 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44384 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44400 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44402 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44412 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37274 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37276 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37292 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:53452 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:37308 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:15:08,451 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:15:08,452 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:15:08,530 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 1.669s
2025-09-30 14:15:10,121 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 1.669s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 1.669s (avg: 1.669s/image)
2025-09-30 14:15:10,122 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 1.669s (avg: 1.669s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:15:10,122 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53453 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:37316 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37328 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37336 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53458 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:33012 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:15:14,728 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:15:14,729 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:15:14,777 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 6.952s
2025-09-30 14:15:21,682 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 6.952s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 6.952s (avg: 6.952s/image)
2025-09-30 14:15:21,682 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 6.952s (avg: 6.952s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:15:21,683 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53459 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33042 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43252 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43258 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53480 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:15:26,608 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:15:26,609 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:15:26,641 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
2025-09-30 14:15:26,764 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
2025-09-30 14:15:26,765 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:15:26,765 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53481 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:43270 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43282 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43294 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43308 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53487 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:15:32,559 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:15:32,560 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:15:32,595 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
2025-09-30 14:15:32,720 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
2025-09-30 14:15:32,721 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:15:32,721 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53488 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34848 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34864 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34878 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34882 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:53493 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:15:37,543 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:15:37,544 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:15:37,580 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
2025-09-30 14:15:37,701 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
2025-09-30 14:15:37,702 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:15:37,702 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53494 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34896 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34910 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34920 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34932 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56042 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56056 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56072 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56088 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53507 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:15:49,263 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:15:49,298 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=84.301
2025-09-30 14:15:49,389 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=84.301
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.090s
2025-09-30 14:15:49,389 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.090s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.093s
2025-09-30 14:15:49,391 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.093s
INFO:     122.35.47.45:53508 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:56104 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56108 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56124 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53512 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:15:54,546 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:15:54,547 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:15:54,582 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
2025-09-30 14:15:54,708 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
2025-09-30 14:15:54,709 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:15:54,709 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53513 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:56406 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56422 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56436 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53518 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:15:58,795 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:15:58,796 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:15:58,830 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
2025-09-30 14:15:58,956 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
2025-09-30 14:15:58,957 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:15:58,957 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53519 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:56442 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56448 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56460 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55042 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53531 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:16:04,838 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:16:04,839 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:16:04,876 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
2025-09-30 14:16:05,009 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
2025-09-30 14:16:05,010 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:16:05,010 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53532 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:55046 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55062 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55068 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55084 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:55090 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53540 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:16:10,709 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:16:10,710 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:16:10,751 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
2025-09-30 14:16:10,875 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
2025-09-30 14:16:10,875 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:16:10,875 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53541 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:55106 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55116 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54548 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53546 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:54550 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:16:16,406 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:16:16,407 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:16:16,448 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:16:16,575 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:16:16,575 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:16:16,575 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53547 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54552 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54560 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54568 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54576 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38634 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38636 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38640 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38646 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38658 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38662 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38672 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44024 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44030 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44034 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44044 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44046 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:44052 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44062 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49704 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49720 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53572 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:16:48,043 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:16:48,045 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:16:48,122 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.237s
2025-09-30 14:16:48,282 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.237s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.237s (avg: 0.237s/image)
2025-09-30 14:16:48,282 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.237s (avg: 0.237s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:16:48,282 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53573 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:49722 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49728 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53578 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:16:52,866 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:16:52,867 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:16:52,909 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
2025-09-30 14:16:53,032 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
2025-09-30 14:16:53,032 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:16:53,033 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53579 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:49742 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40990 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41004 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53590 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:16:57,197 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:16:57,198 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:16:57,240 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
2025-09-30 14:16:57,370 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
2025-09-30 14:16:57,370 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:16:57,370 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53591 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41008 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41018 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41022 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41030 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53609 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:17:03,801 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:17:03,802 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:17:03,845 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
2025-09-30 14:17:03,971 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
2025-09-30 14:17:03,972 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:17:03,972 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53610 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41882 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41898 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53618 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:41904 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:17:08,175 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:17:08,176 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:17:08,225 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.179s
2025-09-30 14:17:08,355 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.179s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.179s (avg: 0.179s/image)
2025-09-30 14:17:08,356 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.179s (avg: 0.179s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:17:08,356 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53619 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41920 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41924 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:41930 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53624 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:17:12,633 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:17:12,634 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:17:12,677 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.173s
2025-09-30 14:17:12,807 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.173s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.173s (avg: 0.173s/image)
2025-09-30 14:17:12,807 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.173s (avg: 0.173s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:17:12,808 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53625 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41934 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45542 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45544 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45546 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45548 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45562 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45572 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45172 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53640 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:17:25,031 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:17:25,032 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:17:25,069 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
2025-09-30 14:17:25,198 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
2025-09-30 14:17:25,198 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:17:25,199 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53641 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:45176 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45190 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45202 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45214 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45222 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57252 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57264 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57270 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57274 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53665 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:57282 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:17:40,552 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:17:40,552 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:17:40,601 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.189s
2025-09-30 14:17:40,742 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.189s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.189s (avg: 0.189s/image)
2025-09-30 14:17:40,742 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.189s (avg: 0.189s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:17:40,742 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53666 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:57290 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:57298 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49860 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53671 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:17:45,218 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:17:45,218 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:17:45,269 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.192s
2025-09-30 14:17:45,411 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.192s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.192s (avg: 0.192s/image)
2025-09-30 14:17:45,412 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.192s (avg: 0.192s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:17:45,412 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53672 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:49864 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49880 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49890 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49904 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53681 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:17:50,561 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:17:50,562 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:17:50,607 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.184s
2025-09-30 14:17:50,747 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.184s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.184s (avg: 0.184s/image)
2025-09-30 14:17:50,747 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.184s (avg: 0.184s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:17:50,747 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53682 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:49916 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49922 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54762 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54770 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54774 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54776 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54792 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54802 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42544 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42552 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42564 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42566 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53699 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:18:09,148 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:18:09,179 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=98.451
2025-09-30 14:18:09,278 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=98.451
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.098s
2025-09-30 14:18:09,278 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.098s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.100s
2025-09-30 14:18:09,278 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.100s
INFO:     122.35.47.45:53700 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:42570 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42572 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42578 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:42580 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59000 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59006 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59008 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53715 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:18:18,298 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:18:18,299 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:18:18,340 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
2025-09-30 14:18:18,463 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
2025-09-30 14:18:18,463 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:18:18,464 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53716 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59018 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59034 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59036 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59052 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42230 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42238 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42250 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42260 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42266 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42270 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46330 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46346 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53735 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:18:37,359 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:18:37,360 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:18:37,413 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.187s
2025-09-30 14:18:37,548 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.187s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.187s (avg: 0.187s/image)
2025-09-30 14:18:37,548 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.187s (avg: 0.187s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:18:37,548 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53736 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:46348 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53741 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:46364 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:18:40,383 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:18:40,384 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:18:40,430 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
2025-09-30 14:18:40,565 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
2025-09-30 14:18:40,566 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:18:40,566 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53742 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:46378 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46384 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:46394 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51732 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51746 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53751 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:18:47,280 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:18:47,281 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:18:47,322 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.175s
2025-09-30 14:18:47,456 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.175s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.175s (avg: 0.175s/image)
2025-09-30 14:18:47,456 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.175s (avg: 0.175s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:18:47,456 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53752 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:51752 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51766 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51776 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53763 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:18:52,347 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:18:52,348 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:18:52,386 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
2025-09-30 14:18:52,518 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
2025-09-30 14:18:52,519 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:18:52,519 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53764 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:51788 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43752 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43760 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53770 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:43774 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:18:57,255 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:18:57,256 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:18:57,295 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
2025-09-30 14:18:57,415 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
2025-09-30 14:18:57,415 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:18:57,416 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53771 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:43778 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43792 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53777 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:19:01,513 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:19:01,513 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:19:01,560 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.178s
2025-09-30 14:19:01,692 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.178s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.178s (avg: 0.178s/image)
2025-09-30 14:19:01,692 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.178s (avg: 0.178s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:19:01,692 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53778 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:43804 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60184 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53783 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:60190 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:19:05,561 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:19:05,562 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:19:05,604 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
2025-09-30 14:19:05,729 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
2025-09-30 14:19:05,729 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:19:05,729 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53784 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:60192 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53788 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:19:09,302 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:19:09,302 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:19:09,338 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
2025-09-30 14:19:09,467 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
2025-09-30 14:19:09,467 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:19:09,467 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53789 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:60198 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60200 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60204 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:60210 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53793 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:19:13,077 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:19:13,077 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:19:13,125 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.175s
2025-09-30 14:19:13,253 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.175s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.175s (avg: 0.175s/image)
2025-09-30 14:19:13,253 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.175s (avg: 0.175s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:19:13,253 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53794 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36462 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36466 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53802 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:36468 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:19:16,766 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:19:16,766 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:19:16,805 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
2025-09-30 14:19:16,927 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
2025-09-30 14:19:16,927 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:19:16,928 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53803 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36472 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36486 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53811 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:19:20,785 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:19:20,786 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:19:20,825 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
2025-09-30 14:19:20,949 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
2025-09-30 14:19:20,949 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:19:20,949 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53812 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36498 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51368 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51370 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51380 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51396 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51412 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51416 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47850 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47864 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47876 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47884 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47886 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47892 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47896 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:47908 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48582 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48596 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48606 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48608 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48616 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48630 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33618 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33630 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33638 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33642 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33656 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33660 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55036 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53847 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:55044 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:20:06,044 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:20:06,085 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=79.315
2025-09-30 14:20:06,186 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=79.315
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.100s
2025-09-30 14:20:06,186 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.100s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.102s
2025-09-30 14:20:06,186 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.102s
INFO:     122.35.47.45:53848 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:55046 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55050 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55056 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55072 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55078 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:58634 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58638 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58640 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58654 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58660 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58672 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46616 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46626 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46634 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46636 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46638 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46644 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46654 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52498 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52514 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52530 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52538 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52552 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52568 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47122 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47136 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:47142 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47158 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47174 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47186 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47198 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53900 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:52564 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:20:55,190 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:20:55,191 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:20:55,290 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.273s
2025-09-30 14:20:55,464 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.273s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.273s (avg: 0.273s/image)
2025-09-30 14:20:55,465 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.273s (avg: 0.273s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:20:55,465 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53901 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:52574 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52582 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52588 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52598 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52606 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58676 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53917 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:21:04,439 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:21:04,440 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:21:04,523 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.252s
2025-09-30 14:21:04,693 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.252s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.252s (avg: 0.252s/image)
2025-09-30 14:21:04,693 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.252s (avg: 0.252s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:21:04,693 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53918 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:58686 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58698 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53926 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:58700 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:21:09,768 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:21:09,769 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:21:09,856 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.258s
2025-09-30 14:21:10,027 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.258s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.258s (avg: 0.258s/image)
2025-09-30 14:21:10,028 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.258s (avg: 0.258s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:21:10,028 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53927 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:58714 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58724 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60716 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60718 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:53931 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:21:14,328 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:21:14,329 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:21:14,400 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.230s
2025-09-30 14:21:14,559 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.230s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.230s (avg: 0.230s/image)
2025-09-30 14:21:14,559 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.230s (avg: 0.230s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:21:14,559 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53932 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:60724 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60742 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60752 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53939 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:21:21,196 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:21:21,197 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:21:21,279 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.252s
2025-09-30 14:21:21,449 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.252s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.252s (avg: 0.252s/image)
2025-09-30 14:21:21,449 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.252s (avg: 0.252s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:21:21,449 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53940 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:60760 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60764 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:53952 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:46966 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:21:26,232 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:21:26,235 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:21:26,319 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.261s
2025-09-30 14:21:26,496 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.261s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.261s (avg: 0.261s/image)
2025-09-30 14:21:26,496 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.261s (avg: 0.261s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:21:26,497 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:53953 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:46978 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46994 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47004 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47014 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47026 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55446 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55452 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55460 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55474 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55486 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55494 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35600 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35608 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:35618 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35620 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35634 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35644 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35654 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35664 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43536 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43548 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43550 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43552 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     221.142.59.41:58257 - "GET /health HTTP/1.1" 404 Not Found
INFO:     127.0.0.1:43556 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43558 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43566 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50946 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50954 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50958 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50962 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50978 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50988 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46480 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46486 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:46496 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46502 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46504 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46510 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46522 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46526 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48044 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48046 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48052 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48062 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48070 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48076 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59476 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54010 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:22:34,621 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:22:34,622 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:22:34,673 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
2025-09-30 14:22:34,795 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
2025-09-30 14:22:34,795 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:22:34,796 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54011 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59492 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59500 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59514 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59526 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54021 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:22:40,038 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:22:40,039 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:22:40,075 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
2025-09-30 14:22:40,201 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
2025-09-30 14:22:40,201 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:22:40,201 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54022 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59534 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59550 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41332 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41344 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:54031 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:41346 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:22:45,726 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:22:45,727 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:22:45,770 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
2025-09-30 14:22:45,892 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
2025-09-30 14:22:45,893 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:22:45,893 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54032 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41352 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41358 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41372 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54040 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:22:51,062 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:22:51,063 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:22:51,096 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.155s
2025-09-30 14:22:51,219 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.155s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.155s (avg: 0.155s/image)
2025-09-30 14:22:51,219 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.155s (avg: 0.155s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:22:51,220 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54041 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41384 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34436 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34442 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54051 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:22:56,749 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:22:56,750 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:22:56,793 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
2025-09-30 14:22:56,917 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
2025-09-30 14:22:56,917 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:22:56,918 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54052 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34456 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34458 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34470 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34480 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34496 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33506 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33516 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33522 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54060 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:23:08,812 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:23:08,847 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=115.641
2025-09-30 14:23:08,939 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=115.641
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.091s
2025-09-30 14:23:08,939 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.091s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.092s
2025-09-30 14:23:08,939 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.092s
INFO:     122.35.47.45:54061 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:33524 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33532 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33542 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33558 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54071 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:23:14,431 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:23:14,432 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:23:14,469 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
2025-09-30 14:23:14,593 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
2025-09-30 14:23:14,593 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:23:14,593 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54072 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:39306 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39314 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:39318 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39332 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54081 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:39336 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:23:19,846 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:23:19,847 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:23:19,884 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.158s
2025-09-30 14:23:20,006 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.158s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.158s (avg: 0.158s/image)
2025-09-30 14:23:20,006 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.158s (avg: 0.158s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:23:20,006 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54082 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:39344 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39356 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52180 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52186 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52200 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52210 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54102 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:52220 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:23:31,330 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:23:31,331 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:23:31,369 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
2025-09-30 14:23:31,491 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
2025-09-30 14:23:31,491 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:23:31,491 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54103 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:52228 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53590 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53600 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54111 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:23:36,982 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:23:36,983 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:23:37,029 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:23:37,151 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:23:37,152 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:23:37,152 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54112 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:53610 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53612 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53614 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53620 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50442 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50456 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50468 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50482 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:50484 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50500 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50516 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40234 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40240 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40246 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40254 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40268 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40274 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57270 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54132 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:05,221 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:05,222 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:05,276 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.189s
2025-09-30 14:24:05,412 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.189s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.189s (avg: 0.189s/image)
2025-09-30 14:24:05,412 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.189s (avg: 0.189s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:05,412 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54133 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:57286 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57294 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54140 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:57304 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:08,849 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:08,850 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:08,905 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
2025-09-30 14:24:09,032 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
2025-09-30 14:24:09,032 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:09,032 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54141 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:57312 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54148 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:57326 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:11,820 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:11,820 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:11,858 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
2025-09-30 14:24:11,978 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
2025-09-30 14:24:11,978 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:11,979 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54149 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:57332 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54153 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:14,842 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:14,843 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:14,882 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
2025-09-30 14:24:15,015 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
2025-09-30 14:24:15,015 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:15,015 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54154 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:35722 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35732 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35742 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:35758 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54162 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:18,697 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:18,697 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:18,735 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.158s
2025-09-30 14:24:18,856 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.158s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.158s (avg: 0.158s/image)
2025-09-30 14:24:18,856 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.158s (avg: 0.158s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:18,856 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54163 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:35766 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54167 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:35778 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:21,276 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:21,276 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:21,321 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
2025-09-30 14:24:21,447 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
2025-09-30 14:24:21,447 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:21,447 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54168 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:35784 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59026 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54177 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:24,726 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:24,726 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:24,762 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
2025-09-30 14:24:24,888 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
2025-09-30 14:24:24,889 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:24,889 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54178 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59030 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59040 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54184 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:59054 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:28,519 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:28,520 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:28,570 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.195s
2025-09-30 14:24:28,715 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.195s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.195s (avg: 0.195s/image)
2025-09-30 14:24:28,716 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.195s (avg: 0.195s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:28,716 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54185 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59070 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59074 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54195 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:32,915 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:32,916 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:32,953 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
2025-09-30 14:24:33,080 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
2025-09-30 14:24:33,081 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:33,081 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54198 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59080 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56102 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56104 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54212 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:37,170 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:37,171 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:37,211 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
2025-09-30 14:24:37,340 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
2025-09-30 14:24:37,340 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:37,341 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54213 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:56106 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56122 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56134 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56138 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54234 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:55236 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:43,796 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:43,797 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:43,838 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.178s
2025-09-30 14:24:43,975 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.178s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.178s (avg: 0.178s/image)
2025-09-30 14:24:43,976 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.178s (avg: 0.178s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:43,976 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54236 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:55250 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55254 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55266 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:54246 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:47,614 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:47,615 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:47,663 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.183s
2025-09-30 14:24:47,799 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.183s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.183s (avg: 0.183s/image)
2025-09-30 14:24:47,799 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.183s (avg: 0.183s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:47,799 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54247 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:55272 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55280 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54253 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:51,655 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:51,656 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:51,708 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.200s
2025-09-30 14:24:51,857 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.200s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.200s (avg: 0.200s/image)
2025-09-30 14:24:51,857 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.200s (avg: 0.200s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:51,857 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54254 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:55294 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55304 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49716 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54260 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:49726 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:24:56,378 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:24:56,379 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:24:56,422 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.182s
2025-09-30 14:24:56,561 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.182s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.182s (avg: 0.182s/image)
2025-09-30 14:24:56,561 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.182s (avg: 0.182s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:24:56,561 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54261 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:49728 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54270 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:00,118 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:00,119 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:00,164 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
2025-09-30 14:25:00,300 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
2025-09-30 14:25:00,300 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:00,301 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54271 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:49750 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49752 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54276 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:39318 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39332 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39340 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39356 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39358 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39370 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39382 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51288 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51302 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:16,608 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:16,608 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:16,666 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.194s
2025-09-30 14:25:16,803 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.194s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.194s (avg: 0.194s/image)
2025-09-30 14:25:16,803 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.194s (avg: 0.194s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:16,804 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54278 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:51304 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51306 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:51314 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54304 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:51318 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:20,975 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:20,976 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:21,032 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.203s
2025-09-30 14:25:21,180 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.203s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.203s (avg: 0.203s/image)
2025-09-30 14:25:21,180 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.203s (avg: 0.203s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:21,181 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54305 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:51320 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56294 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54317 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:24,674 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:24,675 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:24,722 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.187s
2025-09-30 14:25:24,862 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.187s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.187s (avg: 0.187s/image)
2025-09-30 14:25:24,863 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.187s (avg: 0.187s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:24,863 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54318 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:56296 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56302 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56308 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56324 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54331 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:56334 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:32,865 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:32,865 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:32,906 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.173s
2025-09-30 14:25:33,039 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.173s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.173s (avg: 0.173s/image)
2025-09-30 14:25:33,039 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.173s (avg: 0.173s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:33,039 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54332 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38656 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38666 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54343 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:36,570 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:36,571 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:36,613 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.180s
2025-09-30 14:25:36,751 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.180s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.180s (avg: 0.180s/image)
2025-09-30 14:25:36,751 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.180s (avg: 0.180s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:36,751 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54344 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38678 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38690 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54349 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:38698 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:40,477 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:40,478 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:40,520 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
2025-09-30 14:25:40,640 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
2025-09-30 14:25:40,641 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:40,641 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54350 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38712 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51662 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54355 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:43,972 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:43,973 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:44,007 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
2025-09-30 14:25:44,131 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
2025-09-30 14:25:44,131 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:44,131 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54356 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:51668 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51684 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54369 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:51694 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:47,827 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:47,828 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:47,873 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
2025-09-30 14:25:47,999 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
2025-09-30 14:25:48,000 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:48,000 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54370 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:51710 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51712 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54374 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:51,794 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:51,794 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:51,830 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
2025-09-30 14:25:51,958 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
2025-09-30 14:25:51,958 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:51,958 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54375 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:51722 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54379 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:38536 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:25:55,388 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:25:55,389 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:25:55,430 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:25:55,557 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:25:55,558 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:25:55,558 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54380 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38540 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38554 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54387 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:38564 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:26:00,093 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:26:00,094 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:26:00,134 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
2025-09-30 14:26:00,259 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
2025-09-30 14:26:00,260 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:26:00,260 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54388 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38568 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38584 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54392 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:26:04,325 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:26:04,325 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:26:04,359 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
2025-09-30 14:26:04,486 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
2025-09-30 14:26:04,486 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:26:04,487 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54393 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36942 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36948 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54398 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:26:07,780 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:26:07,781 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:26:07,819 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
2025-09-30 14:26:07,946 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
2025-09-30 14:26:07,947 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:26:07,947 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54399 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36960 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36962 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36978 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54404 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:36992 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:26:12,247 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:26:12,247 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:26:12,286 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
2025-09-30 14:26:12,416 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
2025-09-30 14:26:12,417 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:26:12,417 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54405 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:52756 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52760 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54410 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:26:15,687 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:26:15,688 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:26:15,725 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
2025-09-30 14:26:15,851 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
2025-09-30 14:26:15,851 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:26:15,851 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54411 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:52764 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52770 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52778 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:52794 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52796 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52806 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39844 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39850 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39862 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39866 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39868 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39874 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34676 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54450 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:26:35,208 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:26:35,209 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:26:35,267 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.179s
2025-09-30 14:26:35,389 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.179s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.179s (avg: 0.179s/image)
2025-09-30 14:26:35,389 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.179s (avg: 0.179s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:26:35,389 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54451 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34680 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34692 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34704 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54464 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:34714 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:26:40,610 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:26:40,611 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:26:40,658 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:26:40,779 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:26:40,780 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:26:40,780 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54465 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34730 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33354 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33368 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33384 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33390 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33394 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33402 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:33408 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33414 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54475 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:26:53,326 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:26:53,359 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=56.249
2025-09-30 14:26:53,447 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=56.249
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.087s
2025-09-30 14:26:53,447 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.087s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.088s
2025-09-30 14:26:53,447 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.088s
INFO:     122.35.47.45:54476 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:53398 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53400 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53402 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54491 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:53406 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:26:58,858 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:26:58,859 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:26:58,900 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
2025-09-30 14:26:59,026 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
2025-09-30 14:26:59,026 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:26:59,026 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54492 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:53422 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53436 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54772 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54778 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54498 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:27:05,282 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:27:05,283 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:27:05,322 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
2025-09-30 14:27:05,442 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
2025-09-30 14:27:05,442 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:27:05,442 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54499 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54786 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54802 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54818 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54822 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54836 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37052 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54514 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:37062 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37068 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37078 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37092 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37106 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37108 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:27:22,182 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:27:22,183 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:27:22,245 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.184s
2025-09-30 14:27:22,368 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.184s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.184s (avg: 0.184s/image)
2025-09-30 14:27:22,368 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.184s (avg: 0.184s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:27:22,368 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54515 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:37124 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58798 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58802 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58804 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58810 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58824 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58828 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54752 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54764 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54776 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54788 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54538 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:54802 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:27:41,208 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:27:41,208 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:27:41,253 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:27:41,377 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:27:41,377 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:27:41,377 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54539 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54808 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40216 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40220 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54548 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:27:45,218 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:27:45,218 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:27:45,254 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
2025-09-30 14:27:45,378 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
2025-09-30 14:27:45,379 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:27:45,379 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54549 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:40236 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54554 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:40252 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:27:48,099 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:27:48,099 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:27:48,127 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.140s
2025-09-30 14:27:48,240 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.140s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.140s (avg: 0.140s/image)
2025-09-30 14:27:48,240 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.140s (avg: 0.140s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:27:48,240 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54555 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     122.35.47.45:54559 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:27:49,817 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:27:49,817 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:27:49,855 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
2025-09-30 14:27:49,980 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
2025-09-30 14:27:49,980 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:27:49,980 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54560 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:40264 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40278 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40288 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50488 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50502 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:50516 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50528 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50544 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50550 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54575 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:28:00,532 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:28:00,533 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:28:00,574 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
2025-09-30 14:28:00,703 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
2025-09-30 14:28:00,703 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:28:00,704 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54576 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:50566 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50572 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54580 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:28:04,720 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:28:04,720 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:28:04,767 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
2025-09-30 14:28:04,902 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
2025-09-30 14:28:04,902 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:28:04,902 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54581 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:53682 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53696 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53712 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54587 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:28:08,779 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:28:08,780 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:28:08,810 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.144s
2025-09-30 14:28:08,924 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.144s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.144s (avg: 0.144s/image)
2025-09-30 14:28:08,925 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.144s (avg: 0.144s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:28:08,925 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54588 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:53726 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54592 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:53732 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:28:11,366 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:28:11,367 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:28:11,399 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.154s
2025-09-30 14:28:11,521 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.154s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.154s (avg: 0.154s/image)
2025-09-30 14:28:11,522 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.154s (avg: 0.154s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:28:11,522 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54593 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:53734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43806 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54598 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:43818 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43828 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:28:17,437 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:28:17,437 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:28:17,483 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
2025-09-30 14:28:17,604 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
2025-09-30 14:28:17,604 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:28:17,605 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54600 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:43842 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43854 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43866 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43872 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40168 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40178 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:40180 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40184 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40196 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40206 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40212 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52388 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52394 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52404 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52418 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52432 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52436 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59840 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59856 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59866 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59880 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59884 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59894 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59896 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49300 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49308 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49324 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49338 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:49340 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49356 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49360 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49374 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53346 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53352 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53354 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53362 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53372 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53376 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38888 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38892 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38904 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38914 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54673 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:29:19,219 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:29:19,248 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=67.038
2025-09-30 14:29:19,347 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=67.038
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.098s
2025-09-30 14:29:19,347 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.098s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.100s
2025-09-30 14:29:19,347 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.100s
INFO:     122.35.47.45:54674 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:38924 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38926 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38938 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44528 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44534 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44536 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44546 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:44548 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44556 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44568 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44584 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60042 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60050 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60052 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60066 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60070 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60082 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34768 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34780 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34786 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34796 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34812 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34826 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37836 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37846 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37848 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37856 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:37872 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54751 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:30:00,357 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:30:00,358 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:30:00,419 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.192s
2025-09-30 14:30:00,550 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.192s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.192s (avg: 0.192s/image)
2025-09-30 14:30:00,550 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.192s (avg: 0.192s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:30:00,550 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54752 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:37886 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37896 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54764 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:30:03,111 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:30:03,111 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:30:03,151 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
2025-09-30 14:30:03,278 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
2025-09-30 14:30:03,278 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:30:03,278 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54765 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54014 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54016 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54026 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54774 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:30:07,484 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:30:07,484 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:30:07,521 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
2025-09-30 14:30:07,648 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
2025-09-30 14:30:07,648 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:30:07,648 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54775 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54034 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54038 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54046 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54056 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54066 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54801 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:33402 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:30:15,394 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:30:15,395 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:30:15,447 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.190s
2025-09-30 14:30:15,585 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.190s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.190s (avg: 0.190s/image)
2025-09-30 14:30:15,585 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.190s (avg: 0.190s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:30:15,586 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54802 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33404 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33406 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33420 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54818 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:30:20,688 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:30:20,689 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:30:20,727 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
2025-09-30 14:30:20,859 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
2025-09-30 14:30:20,859 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:30:20,859 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54820 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33432 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33438 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46694 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46708 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46716 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46720 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:46722 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54842 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:30:31,073 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:30:31,074 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:30:31,112 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.155s
2025-09-30 14:30:31,230 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.155s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.155s (avg: 0.155s/image)
2025-09-30 14:30:31,230 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.155s (avg: 0.155s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:30:31,230 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54843 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:46734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46746 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48156 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48168 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48178 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48180 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48182 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48192 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60716 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60724 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60738 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60744 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60748 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60756 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60764 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39772 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39786 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39790 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39794 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39802 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:39818 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39834 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39838 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37746 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37760 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37766 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37770 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37778 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34492 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34498 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34512 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34522 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34528 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34538 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50036 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50042 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50058 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54914 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:50062 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:31:28,695 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:31:28,696 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:31:28,753 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
2025-09-30 14:31:28,877 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
2025-09-30 14:31:28,877 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:31:28,877 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54915 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:50068 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50074 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:50088 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50090 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48024 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48026 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48042 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48046 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48048 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48054 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51656 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54949 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:51658 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:31:46,226 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:31:46,262 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=65.836
2025-09-30 14:31:46,352 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=65.836
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.089s
2025-09-30 14:31:46,352 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.089s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.090s
2025-09-30 14:31:46,352 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.090s
INFO:     122.35.47.45:54950 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:51664 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51674 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51688 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51694 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54966 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:40534 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:31:53,803 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:31:53,804 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:31:53,835 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
2025-09-30 14:31:53,960 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
2025-09-30 14:31:53,961 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:31:53,961 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54967 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:40536 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40542 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40558 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:54987 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:31:59,432 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:31:59,433 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:31:59,464 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.152s
2025-09-30 14:31:59,585 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.152s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.152s (avg: 0.152s/image)
2025-09-30 14:31:59,585 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.152s (avg: 0.152s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:31:59,586 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:54988 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:40560 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40572 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:40580 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40592 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45096 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45098 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45106 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45116 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45128 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34696 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34704 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34712 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34718 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34746 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48504 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48506 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48520 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48532 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48542 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48544 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:48550 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39682 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55061 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:32:34,526 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:32:34,527 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:32:34,584 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.196s
2025-09-30 14:32:34,723 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.196s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.196s (avg: 0.196s/image)
2025-09-30 14:32:34,723 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.196s (avg: 0.196s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:32:34,723 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55062 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:39694 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39698 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39714 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39720 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39730 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55078 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:32:42,519 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:32:42,519 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:32:42,564 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.185s
2025-09-30 14:32:42,705 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.185s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.185s (avg: 0.185s/image)
2025-09-30 14:32:42,705 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.185s (avg: 0.185s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:32:42,705 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55079 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:39734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50314 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50324 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50328 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50344 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50352 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55105 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:50360 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:32:52,180 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:32:52,181 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:32:52,222 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.176s
2025-09-30 14:32:52,357 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.176s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.176s (avg: 0.176s/image)
2025-09-30 14:32:52,358 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.176s (avg: 0.176s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:32:52,358 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55106 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33738 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33748 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55112 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:32:55,595 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:32:55,595 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:32:55,632 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
2025-09-30 14:32:55,757 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
2025-09-30 14:32:55,757 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:32:55,757 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55113 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33760 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33770 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33772 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33780 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:55124 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:33:00,777 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:33:00,778 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:33:00,821 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.175s
2025-09-30 14:33:00,953 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.175s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.175s (avg: 0.175s/image)
2025-09-30 14:33:00,953 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.175s (avg: 0.175s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:33:00,953 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55125 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33792 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33798 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45454 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55141 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:45460 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:33:06,743 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:33:06,744 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:33:06,791 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.189s
2025-09-30 14:33:06,933 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.189s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.189s (avg: 0.189s/image)
2025-09-30 14:33:06,934 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.189s (avg: 0.189s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:33:06,934 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55142 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:45474 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45488 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55148 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:45502 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45518 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45530 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58908 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58920 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58928 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58932 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58948 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58960 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:33:23,356 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:33:23,357 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:33:23,410 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.187s
2025-09-30 14:33:23,544 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.187s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.187s (avg: 0.187s/image)
2025-09-30 14:33:23,545 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.187s (avg: 0.187s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:33:23,545 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55149 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:39866 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39880 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39894 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39898 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39910 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39912 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:39920 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:39934 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47714 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47720 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47728 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47740 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47742 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47754 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41460 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41468 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41470 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41472 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41484 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41500 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45026 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45028 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45030 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45046 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45050 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45056 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45064 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:45068 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55229 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:34:02,857 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(723, 723, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:34:02,884 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(723, 723, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=103.363
2025-09-30 14:34:02,978 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=103.363
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.093s
2025-09-30 14:34:02,978 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.093s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.094s
2025-09-30 14:34:02,978 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.094s
INFO:     122.35.47.45:55230 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:48492 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48502 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48510 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55240 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:34:08,518 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:34:08,519 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:34:08,557 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
2025-09-30 14:34:08,691 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
2025-09-30 14:34:08,691 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:34:08,691 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55241 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:48512 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48518 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48530 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48544 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34650 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55250 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:34:15,441 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:34:15,442 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:34:15,490 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
2025-09-30 14:34:15,623 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.181s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
2025-09-30 14:34:15,623 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.181s (avg: 0.181s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:34:15,623 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55251 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34652 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34662 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34678 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34682 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55258 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:34692 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57456 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57464 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57474 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57476 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57490 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57506 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57522 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:34:31,692 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:34:31,692 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:34:31,738 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.197s
2025-09-30 14:34:31,890 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.197s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.197s (avg: 0.197s/image)
2025-09-30 14:34:31,890 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.197s (avg: 0.197s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:34:31,890 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55259 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:57538 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60274 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60276 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60292 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60304 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60308 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60320 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60322 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56590 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56598 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56600 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56604 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56610 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56624 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55312 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:34:54,266 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:34:54,267 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:34:54,315 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
2025-09-30 14:34:54,430 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
2025-09-30 14:34:54,431 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:34:54,431 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55313 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:43252 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43256 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55320 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:43260 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:34:57,541 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:34:57,542 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:34:57,593 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.176s
2025-09-30 14:34:57,718 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.176s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.176s (avg: 0.176s/image)
2025-09-30 14:34:57,718 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.176s (avg: 0.176s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:34:57,719 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55321 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:43262 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43264 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43274 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43280 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:58706 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58708 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58718 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58750 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58752 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55351 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:58760 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:35:12,827 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:35:12,827 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:35:12,869 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.173s
2025-09-30 14:35:13,000 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.173s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.173s (avg: 0.173s/image)
2025-09-30 14:35:13,001 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.173s (avg: 0.173s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:35:13,001 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55352 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54570 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55359 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:54578 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:35:16,014 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:35:16,015 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:35:16,053 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
2025-09-30 14:35:16,181 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
2025-09-30 14:35:16,181 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:35:16,182 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55360 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54588 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54590 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54592 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54608 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54620 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42792 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42798 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42802 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42808 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42822 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42834 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42850 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:59494 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59502 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59516 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59532 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59536 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59552 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54886 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54896 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54898 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55414 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:35:47,135 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:35:47,170 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=115.828
2025-09-30 14:35:47,269 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=115.828
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.098s
2025-09-30 14:35:47,270 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.098s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.100s
2025-09-30 14:35:47,270 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.100s
INFO:     122.35.47.45:55415 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:54910 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54914 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54930 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55422 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:54934 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:35:53,282 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:35:53,283 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:35:53,326 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
2025-09-30 14:35:53,450 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
2025-09-30 14:35:53,451 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:35:53,451 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55424 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34364 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34368 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34382 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34398 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55433 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:35:59,276 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:35:59,276 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:35:59,325 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
2025-09-30 14:35:59,449 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
2025-09-30 14:35:59,449 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:35:59,449 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55434 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34402 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34406 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34416 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34424 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:55444 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:36:04,181 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:36:04,182 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:36:04,224 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
2025-09-30 14:36:04,347 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
2025-09-30 14:36:04,347 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:36:04,347 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55445 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41338 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41342 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41354 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41360 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41368 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41372 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56876 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56890 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56898 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56912 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56928 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56930 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56940 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59036 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59046 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59054 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55482 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:59064 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:36:29,491 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:36:29,492 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:36:29,548 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.188s
2025-09-30 14:36:29,680 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.188s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.188s (avg: 0.188s/image)
2025-09-30 14:36:29,680 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.188s (avg: 0.188s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:36:29,681 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55483 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59068 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59078 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59092 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59106 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:55489 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:36:33,888 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:36:33,889 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:36:33,925 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
2025-09-30 14:36:34,054 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
2025-09-30 14:36:34,055 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:36:34,055 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55490 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:50466 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50468 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55497 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:36:38,188 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:36:38,189 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:36:38,227 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
2025-09-30 14:36:38,358 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
2025-09-30 14:36:38,358 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:36:38,358 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55498 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:50478 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50480 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50482 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55508 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:36:42,027 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:36:42,028 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:36:42,066 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
2025-09-30 14:36:42,194 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
2025-09-30 14:36:42,195 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:36:42,195 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55509 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:50484 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36496 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55514 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:36:45,155 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:36:45,156 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:36:45,193 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
2025-09-30 14:36:45,321 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
2025-09-30 14:36:45,321 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:36:45,322 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55515 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36502 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36508 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36510 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55521 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:36:49,313 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:36:49,314 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:36:49,352 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:36:49,482 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:36:49,482 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:36:49,482 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55522 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36518 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36530 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41018 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55532 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:36:54,358 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:36:54,359 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:36:54,412 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.192s
2025-09-30 14:36:54,551 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.192s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.192s (avg: 0.192s/image)
2025-09-30 14:36:54,552 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.192s (avg: 0.192s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:36:54,552 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55533 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41024 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41032 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41038 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55547 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:36:58,234 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:36:58,234 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:36:58,270 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
2025-09-30 14:36:58,399 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
2025-09-30 14:36:58,399 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:36:58,400 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55548 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41040 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41046 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55558 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:37:01,934 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:37:01,934 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:37:01,971 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
2025-09-30 14:37:02,102 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
2025-09-30 14:37:02,102 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:37:02,103 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55559 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41058 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45668 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45678 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:45684 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45690 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45692 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45706 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45718 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45732 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59600 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59602 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59606 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59622 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59638 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59642 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52944 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52946 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52952 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52966 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52976 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52980 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52984 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38116 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:38126 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38128 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38138 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38142 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38148 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38150 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47244 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47250 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47262 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47268 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47276 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55632 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:47284 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:37:51,904 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:37:51,905 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:37:51,963 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.182s
2025-09-30 14:37:52,087 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.182s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.182s (avg: 0.182s/image)
2025-09-30 14:37:52,088 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.182s (avg: 0.182s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:37:52,088 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55633 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38006 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38008 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38018 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38028 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55657 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:37:58,607 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:37:58,608 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:37:58,647 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
2025-09-30 14:37:58,770 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.162s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
2025-09-30 14:37:58,770 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.162s (avg: 0.162s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:37:58,770 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55658 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38034 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38038 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38046 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55676 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:48514 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:38:03,889 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:38:03,890 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:38:03,925 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
2025-09-30 14:38:04,046 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
2025-09-30 14:38:04,047 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:38:04,047 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55677 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:48528 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:48538 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48554 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55686 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:48566 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:38:09,143 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:38:09,145 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:38:09,182 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
2025-09-30 14:38:09,304 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
2025-09-30 14:38:09,305 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:38:09,305 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55687 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:48570 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48574 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55148 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55162 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55168 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55172 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55186 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55700 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:38:22,168 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:38:22,211 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=37.420
2025-09-30 14:38:22,306 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=37.420
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.094s
2025-09-30 14:38:22,307 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.094s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.096s
2025-09-30 14:38:22,307 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.096s
INFO:     122.35.47.45:55701 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:55202 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42578 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42594 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42598 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42614 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42622 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42628 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44852 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44856 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:44872 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44876 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44878 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44882 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44898 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41808 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41818 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41830 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41842 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41856 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41872 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35454 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35458 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35472 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35476 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35488 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55769 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:01,961 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:01,962 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:02,023 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.206s
2025-09-30 14:39:02,169 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.206s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.206s (avg: 0.206s/image)
2025-09-30 14:39:02,169 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.206s (avg: 0.206s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:02,169 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55770 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:35494 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35504 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53402 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:55778 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:04,978 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:04,979 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:05,016 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:39:05,147 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:39:05,147 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:05,148 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55779 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:53408 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53412 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55786 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:08,209 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:08,210 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:08,246 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
2025-09-30 14:39:08,376 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
2025-09-30 14:39:08,376 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:08,377 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55792 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:53424 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53434 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55797 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:53436 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:53446 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33048 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33058 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33066 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33068 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33072 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:20,802 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:20,803 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:20,861 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.192s
2025-09-30 14:39:20,996 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.192s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.192s (avg: 0.192s/image)
2025-09-30 14:39:20,996 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.192s (avg: 0.192s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:20,996 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55798 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33074 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54818 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55827 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:24,991 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:24,992 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:25,034 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
2025-09-30 14:39:25,163 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
2025-09-30 14:39:25,164 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:25,164 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55831 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54822 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54824 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54830 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55837 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:29,813 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:29,813 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:29,856 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
2025-09-30 14:39:29,985 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
2025-09-30 14:39:29,985 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:29,985 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55838 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54840 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54848 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59368 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59378 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:59384 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55848 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:36,311 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:36,312 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:36,355 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.174s
2025-09-30 14:39:36,486 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.174s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.174s (avg: 0.174s/image)
2025-09-30 14:39:36,487 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.174s (avg: 0.174s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:36,487 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55849 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59394 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59402 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55870 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:59410 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:39,773 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:39,774 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:39,812 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
2025-09-30 14:39:39,942 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
2025-09-30 14:39:39,942 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:39,942 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55873 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59414 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55888 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:43,315 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:43,316 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:43,354 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
2025-09-30 14:39:43,487 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
2025-09-30 14:39:43,487 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:43,487 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55889 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:60308 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60316 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55894 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:60322 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:46,656 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:46,656 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:46,703 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.177s
2025-09-30 14:39:46,834 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.177s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.177s (avg: 0.177s/image)
2025-09-30 14:39:46,834 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.177s (avg: 0.177s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:46,834 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55895 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:60336 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60350 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55899 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:50,341 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:50,341 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:50,387 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.178s
2025-09-30 14:39:50,520 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.178s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.178s (avg: 0.178s/image)
2025-09-30 14:39:50,520 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.178s (avg: 0.178s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:50,520 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55900 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:60364 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47950 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55907 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:54,923 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:54,924 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:54,963 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
2025-09-30 14:39:55,092 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
2025-09-30 14:39:55,092 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:55,092 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55908 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:47952 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47954 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47960 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55914 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:39:59,497 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:39:59,497 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:39:59,536 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
2025-09-30 14:39:59,666 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
2025-09-30 14:39:59,666 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:39:59,667 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55915 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:47964 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47978 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33040 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33044 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:55930 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:04,603 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:04,604 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:04,642 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
2025-09-30 14:40:04,775 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
2025-09-30 14:40:04,775 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:04,776 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55931 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33056 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33060 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33062 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55948 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:09,263 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:09,264 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:09,301 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
2025-09-30 14:40:09,429 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
2025-09-30 14:40:09,429 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:09,429 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55949 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33078 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33086 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55961 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:46980 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:13,815 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:13,816 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:13,855 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
2025-09-30 14:40:13,985 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
2025-09-30 14:40:13,985 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:13,986 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55962 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:46982 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46986 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55968 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:18,177 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:18,178 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:18,215 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
2025-09-30 14:40:18,344 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.166s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
2025-09-30 14:40:18,344 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.166s (avg: 0.166s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:18,344 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55969 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:46996 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47000 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55975 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:21,910 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:21,911 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:21,949 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
2025-09-30 14:40:22,079 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
2025-09-30 14:40:22,079 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:22,079 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55976 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:47014 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38618 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38626 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38634 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55987 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:27,236 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:27,237 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:27,275 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:40:27,405 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:40:27,405 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:27,405 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55988 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38650 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38656 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:55992 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:30,748 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:30,749 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:30,799 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.184s
2025-09-30 14:40:30,933 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.184s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.184s (avg: 0.184s/image)
2025-09-30 14:40:30,933 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.184s (avg: 0.184s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:30,934 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55993 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38668 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38672 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52794 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52796 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:55997 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:35,129 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:35,130 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:35,170 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:40:35,299 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:40:35,299 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:35,299 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:55998 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:52810 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52826 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56005 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:52832 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:39,023 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:39,024 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:39,065 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.176s
2025-09-30 14:40:39,200 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.176s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.176s (avg: 0.176s/image)
2025-09-30 14:40:39,200 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.176s (avg: 0.176s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:39,200 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56006 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:52846 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52856 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56011 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:43,701 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:43,702 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:43,744 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
2025-09-30 14:40:43,863 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
2025-09-30 14:40:43,864 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:43,864 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56012 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54570 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54574 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54586 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56016 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:47,550 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:47,551 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:47,590 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:40:47,719 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:40:47,720 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:47,720 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56017 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54592 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54598 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54604 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56022 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:52,727 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:52,728 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:52,769 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
2025-09-30 14:40:52,899 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
2025-09-30 14:40:52,899 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:52,900 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56023 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54612 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46250 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46260 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46276 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56029 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:40:57,796 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:40:57,796 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:40:57,834 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:40:57,964 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:40:57,965 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:40:57,965 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56030 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:46280 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46286 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56036 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:41:01,068 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:41:01,069 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:41:01,105 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
2025-09-30 14:41:01,233 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
2025-09-30 14:41:01,233 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:41:01,233 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56037 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:46302 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46312 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56042 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:40972 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:41:05,323 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:41:05,323 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:41:05,362 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:41:05,492 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:41:05,492 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:41:05,492 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56043 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:40986 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40990 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:40992 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56055 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:41006 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:41:09,707 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:41:09,708 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:41:09,745 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
2025-09-30 14:41:09,875 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.167s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
2025-09-30 14:41:09,875 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.167s (avg: 0.167s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:41:09,875 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56056 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:41014 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41028 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35316 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35320 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35324 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35332 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35340 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35346 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35358 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46676 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46678 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46688 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46698 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46714 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46716 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35662 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35670 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35674 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35680 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:35688 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35690 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35702 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:35710 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49198 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49208 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49224 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49234 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49238 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:49248 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36670 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36684 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36686 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36700 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36710 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36724 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36734 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59930 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59946 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59950 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59964 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:56132 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:42:08,718 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 600, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:42:08,747 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 600, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=164.486
2025-09-30 14:42:08,838 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=164.486
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.091s
2025-09-30 14:42:08,839 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.091s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.092s
2025-09-30 14:42:08,839 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.092s
INFO:     122.35.47.45:56134 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:59980 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59984 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60000 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60002 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56142 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:42:14,896 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:42:14,897 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:42:14,933 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.155s
2025-09-30 14:42:15,052 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.155s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.155s (avg: 0.155s/image)
2025-09-30 14:42:15,053 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.155s (avg: 0.155s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:42:15,053 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56143 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:44254 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44266 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44278 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44292 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44300 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44314 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40924 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40938 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40940 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40942 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40950 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40956 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40970 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40694 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40698 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40702 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:40712 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40714 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40722 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40724 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60522 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60538 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60554 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60558 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60566 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:60574 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56190 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:42:53,530 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:42:53,531 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:42:53,582 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.180s
2025-09-30 14:42:53,711 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.180s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.180s (avg: 0.180s/image)
2025-09-30 14:42:53,711 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.180s (avg: 0.180s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:42:53,711 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56191 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:56914 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56926 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56938 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56946 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56201 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:42:58,719 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:42:58,720 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:42:58,767 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.184s
2025-09-30 14:42:58,904 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.184s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.184s (avg: 0.184s/image)
2025-09-30 14:42:58,905 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.184s (avg: 0.184s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:42:58,905 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56202 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:56958 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56970 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56982 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47562 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47576 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47588 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47604 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:47608 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47618 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47634 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47640 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57938 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56235 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:43:15,454 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:43:15,455 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:43:15,503 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.180s
2025-09-30 14:43:15,636 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.180s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.180s (avg: 0.180s/image)
2025-09-30 14:43:15,636 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.180s (avg: 0.180s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:43:15,636 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56236 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:57944 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57958 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57968 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56243 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:43:19,778 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:43:19,779 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:43:19,822 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
2025-09-30 14:43:19,945 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
2025-09-30 14:43:19,946 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:43:19,946 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56244 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:57984 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57994 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:32800 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:32812 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:32824 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56257 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:43:27,711 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:43:27,711 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:43:27,750 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
2025-09-30 14:43:27,877 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.165s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
2025-09-30 14:43:27,877 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.165s (avg: 0.165s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:43:27,878 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56258 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:32830 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:32838 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56262 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:43:31,150 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:43:31,151 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:43:31,190 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
2025-09-30 14:43:31,322 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
2025-09-30 14:43:31,322 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:43:31,323 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56263 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:32852 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:32866 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48470 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56273 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:43:35,975 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:43:35,975 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:43:36,027 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.191s
2025-09-30 14:43:36,167 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.191s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.191s (avg: 0.191s/image)
2025-09-30 14:43:36,168 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.191s (avg: 0.191s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:43:36,168 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56274 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:48486 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48502 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48508 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:48512 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48516 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56285 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:43:41,964 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:43:41,965 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:43:42,006 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.175s
2025-09-30 14:43:42,140 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.175s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.175s (avg: 0.175s/image)
2025-09-30 14:43:42,140 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.175s (avg: 0.175s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:43:42,141 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56286 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:48522 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34344 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34346 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56291 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:43:45,785 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:43:45,785 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:43:45,826 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
2025-09-30 14:43:45,955 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
2025-09-30 14:43:45,955 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:43:45,955 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56292 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34362 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34376 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34390 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56297 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:43:50,330 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:43:50,330 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:43:50,371 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:43:50,499 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:43:50,499 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:43:50,499 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56298 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34402 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34406 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56302 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:43:53,616 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:43:53,617 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:43:53,658 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.176s
2025-09-30 14:43:53,793 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.176s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.176s (avg: 0.176s/image)
2025-09-30 14:43:53,793 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.176s (avg: 0.176s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:43:53,794 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56303 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:37078 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37080 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37086 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37096 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56313 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:44:00,406 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:44:00,407 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:44:00,444 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
2025-09-30 14:44:00,570 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
2025-09-30 14:44:00,571 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:44:00,571 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56314 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:37098 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37110 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36252 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56318 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:44:04,109 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:44:04,110 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:44:04,155 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.180s
2025-09-30 14:44:04,291 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.180s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.180s (avg: 0.180s/image)
2025-09-30 14:44:04,291 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.180s (avg: 0.180s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:44:04,291 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56319 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36256 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36264 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36268 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36280 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:56323 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:44:08,441 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:44:08,442 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:44:08,484 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:44:08,611 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:44:08,611 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:44:08,611 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56324 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36284 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36298 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56332 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:44:12,462 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:44:12,462 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:44:12,504 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.174s
2025-09-30 14:44:12,637 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.174s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.174s (avg: 0.174s/image)
2025-09-30 14:44:12,637 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.174s (avg: 0.174s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:44:12,637 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56333 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36308 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54594 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54598 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56340 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:44:16,794 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:44:16,795 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:44:16,828 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.150s
2025-09-30 14:44:16,946 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.150s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.150s (avg: 0.150s/image)
2025-09-30 14:44:16,946 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.150s (avg: 0.150s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:44:16,946 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56341 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:54606 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54618 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54624 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54632 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:54648 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40770 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40786 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40788 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40792 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40804 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40816 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46334 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46340 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46346 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46352 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46358 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:46364 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46372 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37930 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37946 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37954 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37966 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56390 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:44:48,707 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:44:48,747 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=127.292
2025-09-30 14:44:48,845 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=127.292
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.097s
2025-09-30 14:44:48,845 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.097s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.098s
2025-09-30 14:44:48,845 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.098s
INFO:     122.35.47.45:56391 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:37970 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37982 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37994 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48436 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56401 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:44:55,248 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:44:55,248 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:44:55,295 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:44:55,416 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:44:55,417 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:44:55,417 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56402 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:48440 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48454 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48456 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48464 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56408 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:45:01,279 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:45:01,280 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:45:01,314 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
2025-09-30 14:45:01,440 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
2025-09-30 14:45:01,440 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:45:01,441 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56409 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:48478 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48492 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55722 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55728 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56413 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:55742 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:45:08,230 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:45:08,230 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:45:08,264 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
2025-09-30 14:45:08,390 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
2025-09-30 14:45:08,391 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:45:08,391 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56414 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:55756 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55760 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:55776 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55790 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51270 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56422 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:45:14,871 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:45:14,871 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:45:14,906 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
2025-09-30 14:45:15,029 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.157s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
2025-09-30 14:45:15,029 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.157s (avg: 0.157s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:45:15,029 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56423 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:51274 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51276 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51278 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51294 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51310 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51312 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42088 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42092 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42094 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42106 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42118 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42128 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42142 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34436 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56448 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:45:36,211 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:45:36,212 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:45:36,263 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:45:36,380 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:45:36,381 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:45:36,381 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56449 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34446 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34450 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34458 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34464 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:56453 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:45:40,183 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:45:40,184 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:45:40,221 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
2025-09-30 14:45:40,341 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
2025-09-30 14:45:40,341 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:45:40,341 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56454 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:34472 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34478 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36666 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36674 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56465 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:45:46,194 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:45:46,195 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:45:46,233 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
2025-09-30 14:45:46,356 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
2025-09-30 14:45:46,356 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:45:46,357 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56466 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36678 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36682 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56473 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:45:50,487 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:45:50,488 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:45:50,524 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
2025-09-30 14:45:50,652 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
2025-09-30 14:45:50,652 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:45:50,653 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56474 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36684 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36698 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:32986 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:32994 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33006 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56488 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:45:57,728 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:45:57,729 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:45:57,763 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.152s
2025-09-30 14:45:57,881 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.152s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.152s (avg: 0.152s/image)
2025-09-30 14:45:57,882 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.152s (avg: 0.152s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:45:57,882 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56489 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33020 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:33028 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56494 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:33044 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:46:01,242 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:46:01,243 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:46:01,274 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.149s
2025-09-30 14:46:01,392 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.149s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.149s (avg: 0.149s/image)
2025-09-30 14:46:01,392 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.149s (avg: 0.149s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:46:01,393 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56495 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:33050 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51520 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51524 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51536 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51544 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51556 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:51562 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:56509 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:51574 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:46:12,142 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:46:12,143 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:46:12,177 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.152s
2025-09-30 14:46:12,296 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.152s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.152s (avg: 0.152s/image)
2025-09-30 14:46:12,296 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.152s (avg: 0.152s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:46:12,296 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56510 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:51576 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58800 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56524 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:46:16,709 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:46:16,710 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:46:16,746 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
2025-09-30 14:46:16,866 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
2025-09-30 14:46:16,866 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:46:16,866 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56525 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:58808 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58810 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58826 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56532 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:58840 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:46:22,059 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:46:22,060 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:46:22,098 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
2025-09-30 14:46:22,216 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
2025-09-30 14:46:22,217 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:46:22,217 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56533 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:58854 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55446 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55462 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55472 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55486 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55496 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:55510 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57010 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57018 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57020 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57024 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57038 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57048 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:57056 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44192 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44196 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44204 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44212 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44220 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44228 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50080 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50086 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50094 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50098 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50102 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:50104 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45256 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45272 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45286 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45296 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45308 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45316 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:45320 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45332 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56612 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:47:14,629 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:47:14,630 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:47:14,679 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
2025-09-30 14:47:14,800 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
2025-09-30 14:47:14,800 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:47:14,801 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56613 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:44140 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44154 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44160 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56619 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:47:18,473 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:47:18,474 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:47:18,513 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
2025-09-30 14:47:18,637 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.163s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
2025-09-30 14:47:18,638 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.163s (avg: 0.163s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:47:18,638 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56620 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:44162 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44178 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56629 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:44194 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:47:23,363 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:47:23,364 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:47:23,403 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
2025-09-30 14:47:23,525 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.161s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
2025-09-30 14:47:23,525 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.161s (avg: 0.161s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:47:23,525 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56630 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59580 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59588 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56642 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:47:26,704 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:47:26,704 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:47:26,742 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
2025-09-30 14:47:26,864 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
2025-09-30 14:47:26,864 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:47:26,865 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56643 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:59600 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59604 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59610 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:59624 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34096 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34102 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34104 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34112 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56650 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-09-30 14:47:39,770 - app.api.endpoints - INFO - 플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
INFO:app.models.bria_rmbg_onnx:배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
2025-09-30 14:47:39,801 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(800, 800, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=104.861
2025-09-30 14:47:39,890 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=104.861
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.088s
2025-09-30 14:47:39,890 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.088s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.089s
2025-09-30 14:47:39,890 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.089s
INFO:     122.35.47.45:56651 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:     127.0.0.1:34118 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34126 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34132 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:56664 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:47:43,655 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:47:43,655 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:47:43,692 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
2025-09-30 14:47:43,816 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
2025-09-30 14:47:43,816 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:47:43,816 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56665 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38892 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38900 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56670 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:38908 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:47:47,465 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:47:47,466 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:47:47,500 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.158s
2025-09-30 14:47:47,624 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.158s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.158s (avg: 0.158s/image)
2025-09-30 14:47:47,624 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.158s (avg: 0.158s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:47:47,624 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56671 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38920 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38936 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56679 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:38946 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:47:51,411 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:47:51,412 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:47:51,461 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
2025-09-30 14:47:51,584 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
2025-09-30 14:47:51,585 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:47:51,585 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56680 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38950 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36320 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56689 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:47:55,562 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:47:55,563 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:47:55,597 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
2025-09-30 14:47:55,722 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
2025-09-30 14:47:55,723 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:47:55,723 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56690 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36332 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36334 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56696 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:36344 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:47:59,767 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:47:59,768 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:47:59,798 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.153s
2025-09-30 14:47:59,921 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.153s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.153s (avg: 0.153s/image)
2025-09-30 14:47:59,921 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.153s (avg: 0.153s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:47:59,922 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56697 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:36346 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:36350 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34740 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34746 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34752 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34758 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34774 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34780 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40636 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40652 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:40654 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40666 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40668 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40684 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40688 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45258 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56717 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:45266 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:48:25,635 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:48:25,636 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:48:25,681 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
2025-09-30 14:48:25,795 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.159s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
2025-09-30 14:48:25,796 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.159s (avg: 0.159s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:48:25,796 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56719 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:45274 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:45282 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56733 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:45290 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:48:31,353 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:48:31,353 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:48:31,388 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.150s
2025-09-30 14:48:31,504 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.150s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.150s (avg: 0.150s/image)
2025-09-30 14:48:31,504 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.150s (avg: 0.150s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:48:31,505 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56734 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:45298 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37974 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56739 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:48:34,495 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:48:34,496 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:48:34,529 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.148s
2025-09-30 14:48:34,645 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.148s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.148s (avg: 0.148s/image)
2025-09-30 14:48:34,645 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.148s (avg: 0.148s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:48:34,645 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56740 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:37988 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:37992 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38000 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56747 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:38004 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:48:40,652 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:48:40,653 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:48:40,689 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.152s
2025-09-30 14:48:40,806 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.152s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.152s (avg: 0.152s/image)
2025-09-30 14:48:40,806 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.152s (avg: 0.152s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:48:40,806 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56748 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38010 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43582 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43598 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:56761 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:43610 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:48:46,263 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:48:46,264 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:48:46,297 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.147s
2025-09-30 14:48:46,411 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.147s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.147s (avg: 0.147s/image)
2025-09-30 14:48:46,412 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.147s (avg: 0.147s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:48:46,412 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56762 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:43612 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43614 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56766 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:43630 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43638 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:43642 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47202 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47216 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:48:57,429 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:48:57,429 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:48:57,471 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
2025-09-30 14:48:57,600 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
2025-09-30 14:48:57,600 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:48:57,601 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56773 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:47226 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47240 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56783 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:47244 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47252 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48954 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48960 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48966 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48968 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48984 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:48998 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:49:12,570 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:49:12,571 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:49:12,615 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
2025-09-30 14:49:12,742 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
2025-09-30 14:49:12,742 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:49:12,743 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56784 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:49002 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46738 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46742 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     122.35.47.45:56791 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:46758 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46764 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46778 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46794 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:49:21,230 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:49:21,231 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:49:21,274 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
2025-09-30 14:49:21,400 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.168s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
2025-09-30 14:49:21,400 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.168s (avg: 0.168s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:49:21,400 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56792 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:46804 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:46810 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56804 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:57360 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57374 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57378 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:57390 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:49:30,302 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:49:30,303 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:49:30,348 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
2025-09-30 14:49:30,475 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
2025-09-30 14:49:30,475 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:49:30,476 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56805 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:57398 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56815 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:49:33,228 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:49:33,228 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:49:33,266 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
2025-09-30 14:49:33,393 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.164s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
2025-09-30 14:49:33,393 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.164s (avg: 0.164s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:49:33,393 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56816 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:47822 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56820 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:47830 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:49:35,760 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:49:35,761 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:49:35,807 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.174s
2025-09-30 14:49:35,935 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.174s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.174s (avg: 0.174s/image)
2025-09-30 14:49:35,936 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.174s (avg: 0.174s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:49:35,936 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56821 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:47832 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:47836 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56829 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:47842 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:49:40,443 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:49:40,444 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:49:40,500 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.182s
2025-09-30 14:49:40,627 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.182s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.182s (avg: 0.182s/image)
2025-09-30 14:49:40,627 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.182s (avg: 0.182s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:49:40,627 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56830 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:47846 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44388 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56859 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:44400 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:44406 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44422 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44428 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:44438 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:49:51,170 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:49:51,171 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:49:51,222 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.179s
2025-09-30 14:49:51,350 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.179s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.179s (avg: 0.179s/image)
2025-09-30 14:49:51,350 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.179s (avg: 0.179s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:49:51,351 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56860 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:44452 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58282 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56905 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:49:54,848 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:49:54,849 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:49:54,895 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
2025-09-30 14:49:55,022 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.172s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
2025-09-30 14:49:55,022 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.172s (avg: 0.172s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:49:55,022 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56906 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:58294 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58310 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56912 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:49:58,136 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:49:58,137 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:49:58,179 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
2025-09-30 14:49:58,307 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.170s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
2025-09-30 14:49:58,307 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.170s (avg: 0.170s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:49:58,308 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56913 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:58314 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:58322 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56925 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:58324 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:50:02,714 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:50:02,715 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:50:02,759 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.173s
2025-09-30 14:50:02,888 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.173s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.173s (avg: 0.173s/image)
2025-09-30 14:50:02,889 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.173s (avg: 0.173s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:50:02,889 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56926 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38464 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38470 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56933 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:     127.0.0.1:38482 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:50:06,776 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:50:06,776 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:50:06,820 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
2025-09-30 14:50:06,946 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.169s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
2025-09-30 14:50:06,946 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.169s (avg: 0.169s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:50:06,946 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56934 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38486 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38496 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56946 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:50:11,709 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:50:11,710 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:50:11,743 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
2025-09-30 14:50:11,871 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.160s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
2025-09-30 14:50:11,871 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.160s (avg: 0.160s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:50:11,872 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56947 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:38498 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40142 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40148 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:40162 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56953 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:50:15,982 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:50:15,983 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:50:16,028 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
2025-09-30 14:50:16,155 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.171s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
2025-09-30 14:50:16,155 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.171s (avg: 0.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:50:16,155 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56954 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:40172 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40188 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     122.35.47.45:56966 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-09-30 14:50:19,430 - app.core.batch_manager - INFO - Creating a new batch with 1 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
2025-09-30 14:50:19,431 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 1). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
2025-09-30 14:50:19,465 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
2025-09-30 14:50:19,588 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.156s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
2025-09-30 14:50:19,588 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.156s (avg: 0.156s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-09-30 14:50:19,588 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO:     122.35.47.45:56967 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:     127.0.0.1:40200 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:40210 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38242 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38252 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38268 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38278 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38288 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:38290 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34426 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34428 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34434 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34450 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34458 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34474 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34490 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52742 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52758 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:52760 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52772 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52776 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52788 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:52790 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34902 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34914 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34918 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34924 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34932 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34944 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:34960 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56662 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56672 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56682 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56692 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56708 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56714 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:56716 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42788 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42798 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO:     127.0.0.1:42810 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42816 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42830 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42844 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:42854 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41162 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41178 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41182 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41192 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:     127.0.0.1:41208 - "GET /api/v1/stats HTTP/1.1" 200 OK