inpaintServer/logs/main_server.log

1374 lines
121 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

WARNING:root:jtop library not found. Jetson monitoring will be limited. Please run 'sudo pip install jetson-stats'
INFO: Started server process [585410]
INFO: Waiting for application startup.
INFO:main:🚀 인페인팅 서버 시작 중...
2025-10-03 04:36:16,043 - main - INFO - 🚀 인페인팅 서버 시작 중...
INFO:main:✅ 공유 객체를 app.state에 저장 완료
2025-10-03 04:36:16,043 - main - INFO - ✅ 공유 객체를 app.state에 저장 완료
INFO:main:🔄 상태 저장 백그라운드 작업 생성 중...
2025-10-03 04:36:16,043 - main - INFO - 🔄 상태 저장 백그라운드 작업 생성 중...
INFO:main:✅ 상태 저장 백그라운드 작업 생성 완료
2025-10-03 04:36:16,044 - main - INFO - ✅ 상태 저장 백그라운드 작업 생성 완료
INFO:main:🚀 세션 풀 초기화 (CUDA 자동 감지)
2025-10-03 04:36:16,044 - main - INFO - 🚀 세션 풀 초기화 (CUDA 자동 감지)
INFO:app.core.session_pool:Initializing dynamic session pools...
2025-10-03 04:36:16,044 - app.core.session_pool - INFO - Initializing dynamic session pools...
INFO:app.core.session_pool:Pre-loading 4 sessions for simple_lama
2025-10-03 04:36:16,044 - app.core.session_pool - INFO - Pre-loading 4 sessions for simple_lama
INFO:main:🔄 상태 저장 백그라운드 작업 시작됨
2025-10-03 04:36:16,044 - main - INFO - 🔄 상태 저장 백그라운드 작업 시작됨
INFO:app.core.session_pool:Creating new session simple_lama_0 for simple_lama...
2025-10-03 04:36:16,045 - 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...
2025-10-03 04:36:17,647 - app.core.session_pool - INFO - Creating new session simple_lama_1 for simple_lama...
INFO:app.core.session_pool:Creating new session simple_lama_2 for simple_lama...
2025-10-03 04:36:17,647 - app.core.session_pool - INFO - Creating new session simple_lama_2 for simple_lama...
INFO:app.core.session_pool:Creating new session simple_lama_3 for simple_lama...
2025-10-03 04:36:17,647 - app.core.session_pool - INFO - Creating new session simple_lama_3 for simple_lama...
INFO:app.models.simple_lama:Loading Simple LAMA model...
2025-10-03 04:36:17,648 - app.models.simple_lama - INFO - Loading Simple LAMA model...
INFO:app.models.simple_lama:실제 SimpleLama 모델 로딩 완료
2025-10-03 04:36:18,603 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
INFO:app.models.simple_lama:Simple LAMA model loaded successfully
2025-10-03 04:36:18,629 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
INFO:app.models.simple_lama:Loading Simple LAMA model...
2025-10-03 04:36:18,629 - app.models.simple_lama - INFO - Loading Simple LAMA model...
INFO:app.models.simple_lama:실제 SimpleLama 모델 로딩 완료
2025-10-03 04:36:19,376 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
INFO:app.models.simple_lama:Simple LAMA model loaded successfully
2025-10-03 04:36:19,398 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
INFO:app.models.simple_lama:Loading Simple LAMA model...
2025-10-03 04:36:19,398 - app.models.simple_lama - INFO - Loading Simple LAMA model...
INFO:app.models.simple_lama:실제 SimpleLama 모델 로딩 완료
2025-10-03 04:36:20,188 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
INFO:app.models.simple_lama:Simple LAMA model loaded successfully
2025-10-03 04:36:20,210 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
INFO:app.models.simple_lama:Loading Simple LAMA model...
2025-10-03 04:36:20,210 - app.models.simple_lama - INFO - Loading Simple LAMA model...
INFO:app.models.simple_lama:실제 SimpleLama 모델 로딩 완료
2025-10-03 04:36:20,936 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
INFO:app.models.simple_lama:Simple LAMA model loaded successfully
2025-10-03 04:36:20,958 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
INFO:app.core.session_pool:Successfully created session simple_lama_0
2025-10-03 04:36:20,958 - 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 (10.8%)
2025-10-03 04:36:20,958 - app.core.session_pool - INFO - Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (10.8%)
INFO:app.core.session_pool:Successfully created session simple_lama_1
2025-10-03 04:36:20,959 - 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 (10.8%)
2025-10-03 04:36:20,959 - app.core.session_pool - INFO - Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (10.8%)
INFO:app.core.session_pool:Successfully created session simple_lama_2
2025-10-03 04:36:20,959 - app.core.session_pool - INFO - Successfully created session simple_lama_2
INFO:app.core.session_pool: Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (10.8%)
2025-10-03 04:36:20,959 - app.core.session_pool - INFO - Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (10.8%)
INFO:app.core.session_pool:Successfully created session simple_lama_3
2025-10-03 04:36:20,959 - app.core.session_pool - INFO - Successfully created session simple_lama_3
INFO:app.core.session_pool: Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (10.8%)
2025-10-03 04:36:20,960 - app.core.session_pool - INFO - Session Created (simple_lama). Status -> simple_lama: 0, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (10.8%)
INFO:app.core.session_pool:Pre-loading 1 sessions for migan
2025-10-03 04:36:20,960 - app.core.session_pool - INFO - Pre-loading 1 sessions for migan
INFO:app.core.session_pool:Creating new session migan_0 for migan...
2025-10-03 04:36:20,960 - app.core.session_pool - INFO - Creating new session migan_0 for migan...
INFO:app.models.migan:Loading MIGAN ONNX model...
2025-10-03 04:36:20,998 - app.models.migan - INFO - Loading MIGAN ONNX model...
INFO:app.models.migan:MIGAN ONNX 런타임 세션 생성 시도...
2025-10-03 04:36:20,998 - app.models.migan - INFO - MIGAN ONNX 런타임 세션 생성 시도...
INFO:app.models.migan:MIGAN ONNX providers 설정: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-10-03 04:36:20,998 - app.models.migan - INFO - MIGAN ONNX providers 설정: ['CUDAExecutionProvider', 'CPUExecutionProvider']
INFO:app.models.migan:MIGAN ONNX 세션 생성 완료. Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-10-03 04:36:21,261 - app.models.migan - INFO - MIGAN ONNX 세션 생성 완료. Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
INFO:app.models.migan:MIGAN ONNX model loaded successfully
2025-10-03 04:36:21,262 - app.models.migan - INFO - MIGAN ONNX model loaded successfully
INFO:app.core.session_pool:Successfully created session migan_0
2025-10-03 04:36:21,262 - app.core.session_pool - INFO - Successfully created session migan_0
INFO:app.core.session_pool: Session Created (migan). Status -> simple_lama: 4, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (11.2%)
2025-10-03 04:36:21,262 - app.core.session_pool - INFO - Session Created (migan). Status -> simple_lama: 4, migan: 0, rembg: 0 | VRAM: 0.0/0.0 GB (11.2%)
INFO:app.core.session_pool:Pre-loading 2 sessions for rembg
2025-10-03 04:36:21,263 - app.core.session_pool - INFO - Pre-loading 2 sessions for rembg
INFO:app.core.session_pool:Creating new session rembg_0 for rembg...
2025-10-03 04:36:21,263 - app.core.session_pool - INFO - Creating new session rembg_0 for rembg...
INFO:app.models.bria_rmbg_onnx:BriaRMBGOnnxProcessor 초기화 완료
2025-10-03 04:36:21,264 - app.models.bria_rmbg_onnx - INFO - BriaRMBGOnnxProcessor 초기화 완료
INFO:app.core.session_pool:Creating new session rembg_1 for rembg...
2025-10-03 04:36:21,264 - app.core.session_pool - INFO - Creating new session rembg_1 for rembg...
INFO:app.models.bria_rmbg_onnx:BriaRMBGOnnxProcessor 초기화 완료
2025-10-03 04:36:21,264 - 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
2025-10-03 04:36:21,264 - 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
2025-10-03 04:36:21,657 - app.models.bria_rmbg_onnx - INFO - Bria RMBG ONNX 세션 생성 완료, Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'] | Input: input, Output: output
INFO:app.models.bria_rmbg_onnx:Bria RMBG ONNX 세션 생성 중... path=app/models/onnx/BriaRMBG1.4_model_fp16.onnx
2025-10-03 04:36:21,657 - 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
2025-10-03 04:36:22,039 - 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
2025-10-03 04:36:22,039 - app.core.session_pool - INFO - Successfully created session rembg_0
INFO:app.core.session_pool: Session Created (rembg). Status -> simple_lama: 4, migan: 1, rembg: 0 | VRAM: 0.0/0.0 GB (13.6%)
2025-10-03 04:36:22,040 - app.core.session_pool - INFO - Session Created (rembg). Status -> simple_lama: 4, migan: 1, rembg: 0 | VRAM: 0.0/0.0 GB (13.6%)
INFO:app.core.session_pool:Successfully created session rembg_1
2025-10-03 04:36:22,040 - app.core.session_pool - INFO - Successfully created session rembg_1
INFO:app.core.session_pool: Session Created (rembg). Status -> simple_lama: 4, migan: 1, rembg: 0 | VRAM: 0.0/0.0 GB (13.6%)
2025-10-03 04:36:22,040 - app.core.session_pool - INFO - Session Created (rembg). Status -> simple_lama: 4, migan: 1, rembg: 0 | VRAM: 0.0/0.0 GB (13.6%)
INFO:app.core.session_pool:Session pools initialized successfully
2025-10-03 04:36:22,041 - app.core.session_pool - INFO - Session pools initialized successfully
INFO:main:✅ 세션 풀 초기화 완료
2025-10-03 04:36:22,041 - main - INFO - ✅ 세션 풀 초기화 완료
INFO:app.core.worker_manager:Starting worker manager...
2025-10-03 04:36:22,041 - app.core.worker_manager - INFO - Starting worker manager...
INFO:app.core.worker_manager:Worker manager started with 6 workers
2025-10-03 04:36:22,041 - app.core.worker_manager - INFO - Worker manager started with 6 workers
INFO:main:✅ 워커 매니저 시작 완료
2025-10-03 04:36:22,041 - main - INFO - ✅ 워커 매니저 시작 완료
INFO:app.core.batch_manager:Starting BatchManager...
2025-10-03 04:36:22,041 - app.core.batch_manager - INFO - Starting BatchManager...
INFO:app.core.batch_manager:BatchManager started successfully.
2025-10-03 04:36:22,041 - app.core.batch_manager - INFO - BatchManager started successfully.
INFO:main:✅ 배치 관리자 시작 완료
2025-10-03 04:36:22,042 - main - INFO - ✅ 배치 관리자 시작 완료
INFO:main:🎉 인페인팅 서버 시작 완료!
2025-10-03 04:36:22,042 - main - INFO - 🎉 인페인팅 서버 시작 완료!
WARNING:app.utils.discord_notifier:Discord 웹훅 URL이 설정되지 않아 알림을 보낼 수 없습니다.
2025-10-03 04:36:22,042 - 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
2025-10-03 04:36:22,042 - 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: 115.138.85.166:62505 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:36:22,633 - 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
2025-10-03 04:36:22,633 - 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
2025-10-03 04:36:22,691 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 1개 이미지 인페인팅 수행
/workspace/inpaintServer/venv/lib/python3.10/site-packages/torch/nn/modules/module.py:1762: UserWarning: ComplexHalf support is experimental and many operators don't support it yet. (Triggered internally at /pytorch/aten/src/ATen/EmptyTensor.cpp:56.)
return forward_call(*args, **kwargs)
/workspace/inpaintServer/app/models/simple_lama.py:226: RuntimeWarning: invalid value encountered in cast
result_np = np.clip(result_np * 255, 0, 255).astype(np.uint8)
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 1.845s
2025-10-03 04:36:24,479 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 1.845s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 1.845s (avg: 1.845s/image)
2025-10-03 04:36:24,480 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 1.845s (avg: 1.845s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:36:24,480 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:62506 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 220.77.167.192:54054 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:36:24,912 - 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
2025-10-03 04:36:24,913 - 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
2025-10-03 04:36:24,931 - 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: 17.521s
2025-10-03 04:36:42,434 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 17.521s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 17.521s (avg: 17.521s/image)
2025-10-03 04:36:42,435 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 17.521s (avg: 17.521s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:36:42,435 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54055 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:41166 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO: 127.0.0.1:54778 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO: 115.138.85.166:62542 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:36:43,156 - 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
2025-10-03 04:36:43,157 - 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
2025-10-03 04:36:43,194 - 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: 0.132s
2025-10-03 04:36:43,289 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.132s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.132s (avg: 0.132s/image)
2025-10-03 04:36:43,289 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.132s (avg: 0.132s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:36:43,290 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:62543 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:60940 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:60956 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 115.138.85.166:62550 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:60958 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:36:46,774 - 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
2025-10-03 04:36:46,774 - 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
2025-10-03 04:36:46,807 - 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: 0.134s
2025-10-03 04:36:46,909 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.134s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.134s (avg: 0.134s/image)
2025-10-03 04:36:46,909 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.134s (avg: 0.134s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:36:46,909 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:62551 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:60960 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:60972 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:60980 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:60986 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54060 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:36:50,455 - 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
2025-10-03 04:36:50,455 - 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
2025-10-03 04:36:50,485 - 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: 0.129s
2025-10-03 04:36:50,585 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.129s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.129s (avg: 0.129s/image)
2025-10-03 04:36:50,585 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.129s (avg: 0.129s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:36:50,586 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54061 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:32770 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:32782 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:62561 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:36:51,434 - 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
2025-10-03 04:36:51,435 - 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
2025-10-03 04:36:51,468 - 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
2025-10-03 04:36:51,580 - 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)
2025-10-03 04:36:51,580 - 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.
2025-10-03 04:36:51,580 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:62563 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:32794 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:32804 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:39468 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:39476 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:39490 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:61860 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 115.138.85.166:62575 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:36:55,597 - 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
2025-10-03 04:36:55,598 - 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
2025-10-03 04:36:55,644 - 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: 0.145s
2025-10-03 04:36:55,744 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.145s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.145s (avg: 0.145s/image)
2025-10-03 04:36:55,744 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.145s (avg: 0.145s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:36:55,744 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61861 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:39496 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:36:56,035 - 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
2025-10-03 04:36:56,036 - 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
2025-10-03 04:36:56,069 - 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: 0.147s
2025-10-03 04:36:56,183 - 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)
2025-10-03 04:36:56,184 - 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.
2025-10-03 04:36:56,184 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:62576 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:39508 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:39522 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54065 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:36:57,511 - 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
2025-10-03 04:36:57,512 - 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
2025-10-03 04:36:57,554 - 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: 0.142s
2025-10-03 04:36:57,654 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.142s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.142s (avg: 0.142s/image)
2025-10-03 04:36:57,655 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.142s (avg: 0.142s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:36:57,655 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54066 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:39530 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:39538 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 112.165.125.222:7903 - "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)
2025-10-03 04:36:59,518 - 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
2025-10-03 04:36:59,538 - 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=52.082
2025-10-03 04:37:07,441 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=52.082
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 7.902s
2025-10-03 04:37:07,442 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 7.902s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 7.905s
2025-10-03 04:37:07,443 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 7.905s
INFO: 112.165.125.222:7904 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO: 220.77.167.192:54070 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:37:07,757 - 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
2025-10-03 04:37:07,758 - 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
2025-10-03 04:37:07,785 - 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: 0.126s
2025-10-03 04:37:07,884 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.126s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.126s (avg: 0.126s/image)
2025-10-03 04:37:07,885 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.126s (avg: 0.126s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:37:07,885 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54071 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:48874 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:48878 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:48894 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:48896 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 112.165.125.222:7916 - "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)
2025-10-03 04:37:10,856 - 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
2025-10-03 04:37:10,881 - 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=52.305
2025-10-03 04:37:10,961 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=52.305
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.079s
2025-10-03 04:37:10,961 - 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
2025-10-03 04:37:10,961 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.080s
INFO: 112.165.125.222:7917 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO: 127.0.0.1:48908 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:48910 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:48920 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:48926 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:48942 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO: 112.165.125.222:7923 - "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)
2025-10-03 04:37:15,007 - 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
2025-10-03 04:37:15,030 - 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=39.573
2025-10-03 04:37:15,113 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=39.573
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.083s
2025-10-03 04:37:15,113 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.083s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.084s
2025-10-03 04:37:15,114 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.084s
INFO: 112.165.125.222:7924 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO: 127.0.0.1:54746 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:54748 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:54758 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:54762 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:54766 - "GET /api/v1/realtime_status 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/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:54790 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:54798 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:54802 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:54812 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59108 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59120 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59122 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59130 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59146 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59154 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59158 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59168 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59182 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59192 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59202 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59218 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59220 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:46238 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:46242 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:46256 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:46272 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:46284 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:46286 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:46296 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:61868 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:37:39,354 - 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
2025-10-03 04:37:39,355 - 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
2025-10-03 04:37:39,387 - 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: 0.129s
2025-10-03 04:37:39,485 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.129s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.129s (avg: 0.129s/image)
2025-10-03 04:37:39,485 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.129s (avg: 0.129s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:37:39,485 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61869 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:46312 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:46322 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:46334 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:46342 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:46348 - "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: 127.0.0.1:40456 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:40468 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:40484 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:40494 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:40496 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:62782 - "GET /health HTTP/1.1" 200 OK
INFO: 115.138.85.166:62783 - "GET /health HTTP/1.1" 200 OK
INFO: 220.77.167.192:61873 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:37:48,633 - 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
2025-10-03 04:37:48,633 - 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
2025-10-03 04:37:48,659 - 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: 0.125s
2025-10-03 04:37:48,759 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.125s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.125s (avg: 0.125s/image)
2025-10-03 04:37:48,760 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.125s (avg: 0.125s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:37:48,760 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61874 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:40504 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:40514 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:40516 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:54078 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:40522 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:37:50,892 - 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
2025-10-03 04:37:50,893 - 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
2025-10-03 04:37:50,914 - 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: 0.122s
2025-10-03 04:37:51,016 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.122s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.122s (avg: 0.122s/image)
2025-10-03 04:37:51,016 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.122s (avg: 0.122s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:37:51,016 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54079 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 115.138.36.50:13104 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:37:51,404 - 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
2025-10-03 04:37:51,404 - 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
2025-10-03 04:37:51,427 - 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: 0.131s
2025-10-03 04:37:51,535 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.131s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.131s (avg: 0.131s/image)
2025-10-03 04:37:51,536 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.131s (avg: 0.131s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:37:51,536 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.36.50:13105 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:40528 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:40540 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:40556 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 115.138.36.50:13109 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 220.77.167.192:61878 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:37:53,820 - 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
2025-10-03 04:37:53,821 - 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
2025-10-03 04:37:53,853 - 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: 0.131s
2025-10-03 04:37:53,953 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.131s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.131s (avg: 0.131s/image)
2025-10-03 04:37:53,953 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.131s (avg: 0.131s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:37:53,953 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.36.50:13110 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:42078 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:37:54,127 - 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
2025-10-03 04:37:54,128 - 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
2025-10-03 04:37:54,166 - 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
2025-10-03 04:37:54,268 - 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)
2025-10-03 04:37:54,268 - 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.
2025-10-03 04:37:54,268 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61879 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:42082 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:42094 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:42104 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:42110 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:42112 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:42120 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:42136 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:42148 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:42164 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:42178 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:42194 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:42204 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54086 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:04,098 - 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
2025-10-03 04:38:04,098 - 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
2025-10-03 04:38:04,122 - 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: 0.125s
2025-10-03 04:38:04,223 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.125s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.125s (avg: 0.125s/image)
2025-10-03 04:38:04,224 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.125s (avg: 0.125s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:04,224 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54087 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:37310 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:37320 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:37332 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:61886 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:05,928 - 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
2025-10-03 04:38:05,929 - 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
2025-10-03 04:38:05,954 - 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: 0.124s
2025-10-03 04:38:06,053 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.124s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.124s (avg: 0.124s/image)
2025-10-03 04:38:06,054 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.124s (avg: 0.124s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:06,054 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61887 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:37334 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:37342 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:37352 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:37356 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:54091 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:09,323 - 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
2025-10-03 04:38:09,324 - 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
2025-10-03 04:38:09,349 - 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: 0.131s
2025-10-03 04:38:09,455 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.131s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.131s (avg: 0.131s/image)
2025-10-03 04:38:09,456 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.131s (avg: 0.131s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:09,456 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54092 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:37368 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:37374 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:37376 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:61891 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:10,975 - 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
2025-10-03 04:38:10,975 - 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
2025-10-03 04:38:11,001 - 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: 0.132s
2025-10-03 04:38:11,107 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.132s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.132s (avg: 0.132s/image)
2025-10-03 04:38:11,108 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.132s (avg: 0.132s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:11,108 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61892 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:37382 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:37386 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:49710 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:49712 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO: 127.0.0.1:49714 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:49728 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:54097 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:15,175 - 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
2025-10-03 04:38:15,176 - 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
2025-10-03 04:38:15,209 - 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: 0.138s
2025-10-03 04:38:15,315 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.138s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.138s (avg: 0.138s/image)
2025-10-03 04:38:15,315 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.138s (avg: 0.138s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:15,315 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54098 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 220.77.167.192:61896 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:15,958 - 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
2025-10-03 04:38:15,959 - 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
2025-10-03 04:38:15,986 - 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: 0.131s
2025-10-03 04:38:16,090 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.131s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.131s (avg: 0.131s/image)
2025-10-03 04:38:16,090 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.131s (avg: 0.131s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:16,090 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61897 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:49738 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:49754 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:49758 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:49768 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:49776 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54102 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:49790 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:49800 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:20,880 - 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
2025-10-03 04:38:20,880 - 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
2025-10-03 04:38:20,904 - 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: 0.127s
2025-10-03 04:38:21,008 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.127s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.127s (avg: 0.127s/image)
2025-10-03 04:38:21,008 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.127s (avg: 0.127s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:21,008 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54103 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:49812 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:49826 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:53872 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:53878 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:53888 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:54107 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:53904 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:61905 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:25,971 - 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
2025-10-03 04:38:25,972 - 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
2025-10-03 04:38:25,992 - 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: 0.117s
2025-10-03 04:38:26,089 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.117s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.117s (avg: 0.117s/image)
2025-10-03 04:38:26,090 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.117s (avg: 0.117s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:26,090 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54108 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:26,259 - 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
2025-10-03 04:38:26,260 - 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
2025-10-03 04:38:26,287 - 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: 0.129s
2025-10-03 04:38:26,389 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.129s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.129s (avg: 0.129s/image)
2025-10-03 04:38:26,389 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.129s (avg: 0.129s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:26,389 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61906 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:53906 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:53914 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:63315 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:27,635 - 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
2025-10-03 04:38:27,636 - 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
2025-10-03 04:38:27,659 - 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: 0.121s
2025-10-03 04:38:27,757 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.121s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.121s (avg: 0.121s/image)
2025-10-03 04:38:27,757 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.121s (avg: 0.121s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:27,757 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63316 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:53920 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:53926 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:53936 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:53946 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:61910 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:53952 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:31,417 - 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
2025-10-03 04:38:31,417 - 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
2025-10-03 04:38:31,449 - 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: 0.137s
2025-10-03 04:38:31,555 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.137s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.137s (avg: 0.137s/image)
2025-10-03 04:38:31,555 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.137s (avg: 0.137s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:31,556 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61911 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:53956 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54112 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 112.165.125.222:8096 - "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)
2025-10-03 04:38:32,424 - 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=(720, 600, 3), model_name=briaaiRMBG-1.4
2025-10-03 04:38:32,440 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(720, 600, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=62.445
2025-10-03 04:38:32,516 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=62.445
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.075s
2025-10-03 04:38:32,516 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.075s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.076s
2025-10-03 04:38:32,516 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.076s
INFO: 112.165.125.222:8098 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:32,688 - 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
2025-10-03 04:38:32,689 - 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
2025-10-03 04:38:32,712 - 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: 0.122s
2025-10-03 04:38:32,811 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.122s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.122s (avg: 0.122s/image)
2025-10-03 04:38:32,812 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.122s (avg: 0.122s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:32,812 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54113 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:53960 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:53966 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:63397 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:33,844 - 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
2025-10-03 04:38:33,845 - 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
2025-10-03 04:38:33,867 - 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: 0.123s
2025-10-03 04:38:33,968 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.123s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.123s (avg: 0.123s/image)
2025-10-03 04:38:33,968 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.123s (avg: 0.123s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:33,969 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63398 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:44270 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:44286 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 112.165.125.222:8106 - "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)
2025-10-03 04:38:35,795 - 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=(720, 600, 3), model_name=briaaiRMBG-1.4
2025-10-03 04:38:35,814 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(720, 600, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=56.532
2025-10-03 04:38:35,885 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=56.532
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.071s
2025-10-03 04:38:35,886 - 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
2025-10-03 04:38:35,886 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.072s
INFO: 112.165.125.222:8107 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO: 127.0.0.1:44294 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:44296 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:44302 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:61915 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:37,919 - 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
2025-10-03 04:38:37,920 - 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
2025-10-03 04:38:37,945 - 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: 0.128s
2025-10-03 04:38:38,049 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.128s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.128s (avg: 0.128s/image)
2025-10-03 04:38:38,049 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.128s (avg: 0.128s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:38,049 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61916 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:44310 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 112.165.125.222:8113 - "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)
2025-10-03 04:38:39,323 - 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=(720, 600, 3), model_name=briaaiRMBG-1.4
2025-10-03 04:38:39,345 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(720, 600, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=58.147
2025-10-03 04:38:39,418 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=58.147
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.073s
2025-10-03 04:38:39,418 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.073s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.074s
2025-10-03 04:38:39,419 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.074s
INFO: 112.165.125.222:8114 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO: 127.0.0.1:44318 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:44332 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54117 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:40,337 - 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
2025-10-03 04:38:40,337 - 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
2025-10-03 04:38:40,375 - 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
2025-10-03 04:38:40,487 - 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)
2025-10-03 04:38:40,487 - 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.
2025-10-03 04:38:40,487 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54118 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 115.138.85.166:63538 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:44340 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:40,933 - 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
2025-10-03 04:38:40,934 - 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
2025-10-03 04:38:40,956 - 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: 0.119s
2025-10-03 04:38:41,053 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.119s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.119s (avg: 0.119s/image)
2025-10-03 04:38:41,053 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.119s (avg: 0.119s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:41,054 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63540 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:44348 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:44364 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:44380 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:61920 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:59510 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:43,633 - 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
2025-10-03 04:38:43,633 - 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
2025-10-03 04:38:43,661 - 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: 0.127s
2025-10-03 04:38:43,761 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.127s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.127s (avg: 0.127s/image)
2025-10-03 04:38:43,761 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.127s (avg: 0.127s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:43,762 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61921 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:59514 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59516 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59526 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO: 127.0.0.1:59540 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:63551 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:46,330 - 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
2025-10-03 04:38:46,330 - 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
2025-10-03 04:38:46,351 - 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: 0.118s
2025-10-03 04:38:46,448 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.118s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.118s (avg: 0.118s/image)
2025-10-03 04:38:46,448 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.118s (avg: 0.118s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:46,448 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63552 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:59554 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59568 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59572 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59574 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54122 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:49,538 - 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
2025-10-03 04:38:49,539 - 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
2025-10-03 04:38:49,574 - 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: 0.154s
2025-10-03 04:38:49,692 - 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)
2025-10-03 04:38:49,693 - 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.
2025-10-03 04:38:49,693 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54123 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:59576 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59580 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:59592 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:59602 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:63589 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:59618 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:53,127 - 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
2025-10-03 04:38:53,127 - 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
2025-10-03 04:38:53,151 - 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: 0.122s
2025-10-03 04:38:53,250 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.122s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.122s (avg: 0.122s/image)
2025-10-03 04:38:53,250 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.122s (avg: 0.122s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:53,250 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63592 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:43098 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:43104 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:43112 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:43126 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:54127 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:43140 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:56,972 - 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
2025-10-03 04:38:56,973 - 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
2025-10-03 04:38:56,998 - 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: 0.124s
2025-10-03 04:38:57,097 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.124s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.124s (avg: 0.124s/image)
2025-10-03 04:38:57,097 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.124s (avg: 0.124s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:57,097 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54128 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 112.165.125.222:8136 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:57,334 - 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
2025-10-03 04:38:57,335 - 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
2025-10-03 04:38:57,366 - 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: 0.134s
2025-10-03 04:38:57,469 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.134s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.134s (avg: 0.134s/image)
2025-10-03 04:38:57,469 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.134s (avg: 0.134s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:57,469 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 112.165.125.222:8137 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:43156 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:43158 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:59797 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:43170 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:38:59,112 - 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
2025-10-03 04:38:59,113 - 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
2025-10-03 04:38:59,135 - 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: 0.120s
2025-10-03 04:38:59,233 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.120s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.120s (avg: 0.120s/image)
2025-10-03 04:38:59,233 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.120s (avg: 0.120s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:38:59,234 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:28694 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:43174 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:43180 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:43184 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:43188 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 112.165.125.222:8142 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:02,704 - 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
2025-10-03 04:39:02,704 - 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
2025-10-03 04:39:02,726 - 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: 0.120s
2025-10-03 04:39:02,824 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.120s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.120s (avg: 0.120s/image)
2025-10-03 04:39:02,825 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.120s (avg: 0.120s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:02,825 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 112.165.125.222:8143 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:43202 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:40948 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:40952 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:63642 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:40962 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:05,174 - 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
2025-10-03 04:39:05,175 - 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
2025-10-03 04:39:05,198 - 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: 0.122s
2025-10-03 04:39:05,297 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.122s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.122s (avg: 0.122s/image)
2025-10-03 04:39:05,298 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.122s (avg: 0.122s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:05,298 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63643 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:40968 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:40978 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:40988 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:41004 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:54136 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:08,670 - 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
2025-10-03 04:39:08,671 - 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
2025-10-03 04:39:08,701 - 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: 0.136s
2025-10-03 04:39:08,807 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.136s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.136s (avg: 0.136s/image)
2025-10-03 04:39:08,808 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.136s (avg: 0.136s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:08,808 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54137 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:41018 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.36.50:10913 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:09,382 - 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
2025-10-03 04:39:09,382 - 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
2025-10-03 04:39:09,404 - 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: 0.119s
2025-10-03 04:39:09,501 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.119s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.119s (avg: 0.119s/image)
2025-10-03 04:39:09,502 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.119s (avg: 0.119s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:09,502 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.36.50:10914 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 115.138.85.166:63653 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:41024 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:41036 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:10,307 - 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
2025-10-03 04:39:10,308 - 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
2025-10-03 04:39:10,330 - 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: 0.118s
2025-10-03 04:39:10,426 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.118s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.118s (avg: 0.118s/image)
2025-10-03 04:39:10,427 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.118s (avg: 0.118s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:10,427 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63654 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:41038 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:41040 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.36.50:10918 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:12,548 - 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
2025-10-03 04:39:12,548 - 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
2025-10-03 04:39:12,573 - 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: 0.124s
2025-10-03 04:39:12,673 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.124s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.124s (avg: 0.124s/image)
2025-10-03 04:39:12,674 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.124s (avg: 0.124s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:12,674 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.36.50:10919 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:41050 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:41064 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:60922 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:60936 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:60952 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:60956 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:60970 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:60980 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO: 115.138.85.166:63666 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 220.77.167.192:54145 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 2 jobs.
2025-10-03 04:39:17,975 - app.core.batch_manager - INFO - Creating a new batch with 2 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 2). VRAM: 0.0 GB
2025-10-03 04:39:17,975 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 2). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 2개 이미지 인페인팅 수행
2025-10-03 04:39:18,024 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 2개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 2). VRAM: 0.0 GB | Duration: 0.286s
2025-10-03 04:39:18,262 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 2). VRAM: 0.0 GB | Duration: 0.286s
INFO:app.core.worker_manager:'simple-lama' batch of 2 processed in 0.286s (avg: 0.143s/image)
2025-10-03 04:39:18,262 - app.core.worker_manager - INFO - 'simple-lama' batch of 2 processed in 0.286s (avg: 0.143s/image)
INFO:app.core.batch_manager:Successfully processed batch of 2 jobs.
2025-10-03 04:39:18,262 - app.core.batch_manager - INFO - Successfully processed batch of 2 jobs.
INFO: 220.77.167.192:54146 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 115.138.85.166:63668 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:60988 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:32770 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:32786 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:32798 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:32808 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:32820 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:32826 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54150 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:23,685 - 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
2025-10-03 04:39:23,686 - 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
2025-10-03 04:39:23,711 - 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: 0.128s
2025-10-03 04:39:23,815 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.128s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.128s (avg: 0.128s/image)
2025-10-03 04:39:23,815 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.128s (avg: 0.128s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:23,815 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54151 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:43034 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:43042 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:63680 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:25,525 - 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
2025-10-03 04:39:25,526 - 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
2025-10-03 04:39:25,547 - 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: 0.118s
2025-10-03 04:39:25,644 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.118s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.118s (avg: 0.118s/image)
2025-10-03 04:39:25,644 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.118s (avg: 0.118s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:25,644 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63681 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:43050 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:43066 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:43078 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:61957 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:27,363 - 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
2025-10-03 04:39:27,364 - 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
2025-10-03 04:39:27,385 - 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: 0.116s
2025-10-03 04:39:27,480 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.116s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.116s (avg: 0.116s/image)
2025-10-03 04:39:27,481 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.116s (avg: 0.116s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:27,481 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61958 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:43092 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54155 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:43096 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:43104 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:29,032 - 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
2025-10-03 04:39:29,032 - 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
2025-10-03 04:39:29,059 - 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: 0.130s
2025-10-03 04:39:29,163 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.130s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.130s (avg: 0.130s/image)
2025-10-03 04:39:29,163 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.130s (avg: 0.130s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:29,163 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54156 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:43108 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:43116 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:43118 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:43128 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:43134 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:45358 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:61962 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:34,600 - 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
2025-10-03 04:39:34,601 - 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
2025-10-03 04:39:34,621 - 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: 0.121s
2025-10-03 04:39:34,722 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.121s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.121s (avg: 0.121s/image)
2025-10-03 04:39:34,723 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.121s (avg: 0.121s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:34,723 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:61963 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 220.77.167.192:54160 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:45362 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:45376 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:35,148 - 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
2025-10-03 04:39:35,149 - 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
2025-10-03 04:39:35,176 - 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: 0.125s
2025-10-03 04:39:35,274 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.125s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.125s (avg: 0.125s/image)
2025-10-03 04:39:35,275 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.125s (avg: 0.125s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:35,275 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54161 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:45378 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:45394 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:45398 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:45400 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:45406 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:45420 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 220.77.167.192:54165 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:40,914 - 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
2025-10-03 04:39:40,915 - 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
2025-10-03 04:39:40,940 - 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: 0.120s
2025-10-03 04:39:41,035 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.120s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.120s (avg: 0.120s/image)
2025-10-03 04:39:41,035 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.120s (avg: 0.120s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:41,035 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54166 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:45422 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:45438 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:45454 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:45468 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:35592 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:35604 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:35606 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:54171 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:35618 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:46,379 - 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
2025-10-03 04:39:46,380 - 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
2025-10-03 04:39:46,406 - 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: 0.127s
2025-10-03 04:39:46,508 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.127s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.127s (avg: 0.127s/image)
2025-10-03 04:39:46,508 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.127s (avg: 0.127s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:46,508 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54172 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:35626 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:35640 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:35644 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:35652 - "GET /api/v1/health HTTP/1.1" 200 OK
INFO: 127.0.0.1:35654 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:35660 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:35676 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:35680 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:35686 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:35688 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:35702 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:63771 - "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)
2025-10-03 04:39:53,874 - 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
2025-10-03 04:39:53,898 - 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=103.434
2025-10-03 04:39:53,980 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=103.434
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.081s
2025-10-03 04:39:53,980 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.081s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.083s
2025-10-03 04:39:53,980 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.083s
INFO: 115.138.85.166:63773 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO: 127.0.0.1:47214 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:47220 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:47236 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:47244 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:47256 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:54179 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:39:58,145 - 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
2025-10-03 04:39:58,146 - 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
2025-10-03 04:39:58,175 - 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: 0.135s
2025-10-03 04:39:58,281 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.135s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.135s (avg: 0.135s/image)
2025-10-03 04:39:58,281 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.135s (avg: 0.135s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:39:58,281 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54180 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:47272 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:47288 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:47298 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:47302 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 115.138.85.166:63786 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:47308 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:40:01,557 - 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
2025-10-03 04:40:01,558 - 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
2025-10-03 04:40:01,581 - 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: 0.120s
2025-10-03 04:40:01,678 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.120s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.120s (avg: 0.120s/image)
2025-10-03 04:40:01,678 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.120s (avg: 0.120s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:40:01,678 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63787 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:47324 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:47338 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:51152 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:51156 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:51164 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:51178 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:51186 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 220.77.167.192:54187 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 115.138.85.166:63797 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:40:07,203 - 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
2025-10-03 04:40:07,205 - 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
2025-10-03 04:40:07,241 - 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: 0.134s
2025-10-03 04:40:07,339 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.134s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.134s (avg: 0.134s/image)
2025-10-03 04:40:07,339 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.134s (avg: 0.134s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:40:07,339 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 220.77.167.192:54188 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:51188 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:40:07,557 - 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
2025-10-03 04:40:07,558 - 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
2025-10-03 04:40:07,582 - 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: 0.121s
2025-10-03 04:40:07,679 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.121s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.121s (avg: 0.121s/image)
2025-10-03 04:40:07,679 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.121s (avg: 0.121s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:40:07,679 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.85.166:63798 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:51204 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:51208 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:51212 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:51220 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:51232 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:51238 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:51240 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:57302 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:57306 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:57322 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 127.0.0.1:57328 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 127.0.0.1:57338 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO: 115.138.85.166:63813 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 220.77.167.192:54192 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 2 jobs.
2025-10-03 04:40:17,109 - app.core.batch_manager - INFO - Creating a new batch with 2 jobs.
INFO:app.core.worker_manager:🧠[simple_lama] Batch Inference Start (Size: 2). VRAM: 0.0 GB
2025-10-03 04:40:17,110 - app.core.worker_manager - INFO - 🧠[simple_lama] Batch Inference Start (Size: 2). VRAM: 0.0 GB
INFO:app.models.simple_lama:실제 SimpleLama 모델로 2개 이미지 인페인팅 수행
2025-10-03 04:40:17,163 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 2개 이미지 인페인팅 수행
INFO:app.core.worker_manager:✅[simple_lama] Batch Inference End (Size: 2). VRAM: 0.0 GB | Duration: 18.343s
2025-10-03 04:40:35,453 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 2). VRAM: 0.0 GB | Duration: 18.343s
INFO:app.core.worker_manager:'simple-lama' batch of 2 processed in 18.343s (avg: 9.171s/image)
2025-10-03 04:40:35,454 - app.core.worker_manager - INFO - 'simple-lama' batch of 2 processed in 18.343s (avg: 9.171s/image)
INFO:app.core.batch_manager:Successfully processed batch of 2 jobs.
2025-10-03 04:40:35,454 - app.core.batch_manager - INFO - Successfully processed batch of 2 jobs.
INFO: 115.138.85.166:63814 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 220.77.167.192:54193 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 127.0.0.1:38944 - "GET /api/v1/stats HTTP/1.1" 200 OK
INFO: 112.165.125.222:8250 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 115.138.36.50:45984 - "GET /api/v1/model HTTP/1.1" 200 OK
INFO: 127.0.0.1:38956 - "GET /api/v1/realtime_status HTTP/1.1" 200 OK
INFO:app.core.batch_manager:Creating a new batch with 1 jobs.
2025-10-03 04:40:35,829 - 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
2025-10-03 04:40:35,829 - 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
2025-10-03 04:40:35,855 - 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: 0.125s
2025-10-03 04:40:35,955 - app.core.worker_manager - INFO - ✅[simple_lama] Batch Inference End (Size: 1). VRAM: 0.0 GB | Duration: 0.125s
INFO:app.core.worker_manager:'simple-lama' batch of 1 processed in 0.125s (avg: 0.125s/image)
2025-10-03 04:40:35,955 - app.core.worker_manager - INFO - 'simple-lama' batch of 1 processed in 0.125s (avg: 0.125s/image)
INFO:app.core.batch_manager:Successfully processed batch of 1 jobs.
2025-10-03 04:40:35,955 - app.core.batch_manager - INFO - Successfully processed batch of 1 jobs.
INFO: 115.138.36.50:5053 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO:app.api.endpoints:플러그인 호환 엔드포인트 '/api/v1/run_plugin_gen_image' 호출됨 (모델: rembg)
2025-10-03 04:40:35,981 - 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=(1000, 750, 3), model_name=briaaiRMBG-1.4
2025-10-03 04:40:36,004 - app.models.bria_rmbg_onnx - INFO - 배경제거 시작(Bria ONNX): image.shape=(1000, 750, 3), model_name=briaaiRMBG-1.4
INFO:app.models.bria_rmbg_onnx:Bria ONNX mask stats: min=0, max=255, mean=105.917
2025-10-03 04:40:36,092 - app.models.bria_rmbg_onnx - INFO - Bria ONNX mask stats: min=0, max=255, mean=105.917
INFO:app.models.bria_rmbg_onnx:'bria-rmbg' processed in 0.087s
2025-10-03 04:40:36,092 - app.models.bria_rmbg_onnx - INFO - 'bria-rmbg' processed in 0.087s
INFO:app.core.worker_manager:'rembg (briaaiRMBG-1.4)' processed in 0.089s
2025-10-03 04:40:36,093 - app.core.worker_manager - INFO - 'rembg (briaaiRMBG-1.4)' processed in 0.089s
INFO: 112.165.125.222:8251 - "POST /api/v1/run_plugin_gen_image HTTP/1.1" 200 OK
INFO: Shutting down
INFO: Waiting for application shutdown.
INFO:main:🛑 인페인팅 서버 종료 중...
2025-10-03 04:40:36,316 - main - INFO - 🛑 인페인팅 서버 종료 중...
INFO:app.core.worker_manager:Stopping worker manager...
2025-10-03 04:40:36,317 - app.core.worker_manager - INFO - Stopping worker manager...
INFO:app.core.worker_manager:Worker manager stopped
2025-10-03 04:40:36,317 - app.core.worker_manager - INFO - Worker manager stopped
INFO:main:✅ 워커 매니저 중지 완료
2025-10-03 04:40:36,317 - main - INFO - ✅ 워커 매니저 중지 완료
INFO:app.core.batch_manager:Stopping BatchManager...
2025-10-03 04:40:36,317 - app.core.batch_manager - INFO - Stopping BatchManager...
INFO:app.core.batch_manager:BatchManager stopped.
2025-10-03 04:40:36,318 - app.core.batch_manager - INFO - BatchManager stopped.
INFO:main:✅ 배치 관리자 중지 완료
2025-10-03 04:40:36,318 - main - INFO - ✅ 배치 관리자 중지 완료
INFO:main:👋 인페인팅 서버 종료 완료
2025-10-03 04:40:36,318 - main - INFO - 👋 인페인팅 서버 종료 완료
WARNING:app.utils.discord_notifier:Discord 웹훅 URL이 설정되지 않아 알림을 보낼 수 없습니다.
2025-10-03 04:40:36,318 - app.utils.discord_notifier - WARNING - Discord 웹훅 URL이 설정되지 않아 알림을 보낼 수 없습니다.
INFO: Application shutdown complete.
INFO: Finished server process [585410]