40 lines
31 KiB
JSON
40 lines
31 KiB
JSON
{
|
|
"frames": [
|
|
{
|
|
"file": "frame_000.jpg",
|
|
"time": 0.0,
|
|
"log": "Capturing execution frames: scene_seg_interactive.json\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 3895 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=13 sending model_to_device\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -303MB (now 3148MB) reserved=3520MB peak=5550MB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -1468MB (now 1680MB) reserved=3520MB peak=5550MB\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 567 / 7703 MB"
|
|
},
|
|
{
|
|
"file": "frame_001.jpg",
|
|
"time": 2.34,
|
|
"log": "Capturing execution frames: scene_seg_interactive.json\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 3895 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=13 sending model_to_device\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -303MB (now 3148MB) reserved=3520MB peak=5550MB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -1468MB (now 1680MB) reserved=3520MB peak=5550MB\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 567 / 7703 MB\n Frame 1 saved (frame_000.jpg, t=0.0s)\n Validating workflow...\n [ComfyUI] === /validate endpoint called ===\n Queuing workflow for execution...\n [ComfyUI] Received JSON with keys: ['prompt']\n [ComfyUI] Prompt has 4 nodes\n [ComfyUI] Node 1: LoadImage\n [ComfyUI] Inputs: {\"image\": \"image.png\"}\n [ComfyUI] Node 4: MaskPreview\n [ComfyUI] Inputs: {\"mask\": [\"26\", 0]}\n [ComfyUI] Node 12: LoadSAM3Model\n [ComfyUI] Inputs: {\"precision\": \"auto\", \"compile\": false}\n [ComfyUI] Node 26: SAM3InteractiveCollector\n [ComfyUI] Inputs: {\"multi_prompts_store\": \"[{\\\"positive_points\\\":[{\\\"x\\\":3348.288109906738,\\\"y\\\":2452.2208696844737}],\\\"negative_points\\\":[],\\\"positive_boxes\\\":[],\\\"negative_boxes\\\":[],\\\"name\\\":\\\"Prompt 1\\\"},{\\\"positiv\n [ComfyUI] Generated prompt_id: d3506526-5083-4c61-9bc4-43b3c786251a\n [ComfyUI] Calling execution.validate_prompt()...\n [ComfyUI] Validation result: valid=True\n [ComfyUI] === Validation PASSED ===\n [ComfyUI] got prompt\n [ComfyUI] [comfy-env] Running LoadSAM3Model: precision: 'auto', compile: False\n [ComfyUI] [ComfyUI-SAM3] python: /root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [VRAM] Before LoadSAM3Model: 567 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] sys_path sent to worker: ['/workspaces/SAM3-0918/ComfyUI', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3', '/root/.ce/.pixi/envs/sam3-nodes/lib/python3.12/site-packages', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3']\n [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSAM3Model.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'sam3-nodes', 'python', '/tmp/comfyui_pvenv_2f4orjtw/persistent_worker.py', 'abstract://comfy_worker_bc4edfd21732']...\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_bc4edfd21732 (abstract, no filesystem path)\n [ComfyUI] [ComfyUI-SAM3] Health check: failed\n [ComfyUI] [ComfyUI-SAM3] Socket unhealthy, restarting worker...\n [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload)"
|
|
},
|
|
{
|
|
"file": "frame_002.jpg",
|
|
"time": 4.58,
|
|
"log": "Capturing execution frames: scene_seg_interactive.json\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 3895 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=13 sending model_to_device\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -303MB (now 3148MB) reserved=3520MB peak=5550MB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -1468MB (now 1680MB) reserved=3520MB peak=5550MB\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 567 / 7703 MB\n Frame 1 saved (frame_000.jpg, t=0.0s)\n Validating workflow...\n [ComfyUI] === /validate endpoint called ===\n Queuing workflow for execution...\n [ComfyUI] Received JSON with keys: ['prompt']\n [ComfyUI] Prompt has 4 nodes\n [ComfyUI] Node 1: LoadImage\n [ComfyUI] Inputs: {\"image\": \"image.png\"}\n [ComfyUI] Node 4: MaskPreview\n [ComfyUI] Inputs: {\"mask\": [\"26\", 0]}\n [ComfyUI] Node 12: LoadSAM3Model\n [ComfyUI] Inputs: {\"precision\": \"auto\", \"compile\": false}\n [ComfyUI] Node 26: SAM3InteractiveCollector\n [ComfyUI] Inputs: {\"multi_prompts_store\": \"[{\\\"positive_points\\\":[{\\\"x\\\":3348.288109906738,\\\"y\\\":2452.2208696844737}],\\\"negative_points\\\":[],\\\"positive_boxes\\\":[],\\\"negative_boxes\\\":[],\\\"name\\\":\\\"Prompt 1\\\"},{\\\"positiv\n [ComfyUI] Generated prompt_id: d3506526-5083-4c61-9bc4-43b3c786251a\n [ComfyUI] Calling execution.validate_prompt()...\n [ComfyUI] Validation result: valid=True\n [ComfyUI] === Validation PASSED ===\n [ComfyUI] got prompt\n [ComfyUI] [comfy-env] Running LoadSAM3Model: precision: 'auto', compile: False\n [ComfyUI] [ComfyUI-SAM3] python: /root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [VRAM] Before LoadSAM3Model: 567 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] sys_path sent to worker: ['/workspaces/SAM3-0918/ComfyUI', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3', '/root/.ce/.pixi/envs/sam3-nodes/lib/python3.12/site-packages', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3']\n [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSAM3Model.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'sam3-nodes', 'python', '/tmp/comfyui_pvenv_2f4orjtw/persistent_worker.py', 'abstract://comfy_worker_bc4edfd21732']...\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_bc4edfd21732 (abstract, no filesystem path)\n [ComfyUI] [ComfyUI-SAM3] Health check: failed\n [ComfyUI] [ComfyUI-SAM3] Socket unhealthy, restarting worker...\n [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload)\n Frame 2 saved (frame_001.jpg, t=2.3s)\n [capture-periodic] freeze=1ms shot=145ms unfreeze=3ms saved=True\n [ComfyUI] [worker:ComfyUI-SAM3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=14 sending call_method\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 269 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=15 sending model_to_device\n [ComfyUI] Model 'Sam3VideoInferenceWithInstanceInteractivity_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 269 / 7703 MB\n [ComfyUI] [comfy-env] LoadSAM3Model done (2.40s): result: NodeOutput\n [ComfyUI] [VRAM] After LoadSAM3Model: 269 / 7703 MB\n [ComfyUI] [comfy-env] Running SAM3InteractiveCollector: multi_prompts_store: '[{\"positive_points\":[{\"x\":3348.288109906738,\"y\":2452.220..., sam3_model_config: dict, image: torch.float32 [1,4480,6720,3] cpu, unique_id: '26'\n [ComfyUI] [VRAM] Before SAM3InteractiveCollector: 269 / 7703 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.sam3_interactive.SAM3InteractiveCollector.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'image' shape: torch.Size([1, 4480, 6720, 3])\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=16 sending call_method\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 4480, 6720, 3]\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 4480, 6720, 3])"
|
|
},
|
|
{
|
|
"file": "frame_003.jpg",
|
|
"time": 9.05,
|
|
"log": "Capturing execution frames: scene_seg_interactive.json\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 3895 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=13 sending model_to_device\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -303MB (now 3148MB) reserved=3520MB peak=5550MB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -1468MB (now 1680MB) reserved=3520MB peak=5550MB\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 567 / 7703 MB\n Frame 1 saved (frame_000.jpg, t=0.0s)\n Validating workflow...\n [ComfyUI] === /validate endpoint called ===\n Queuing workflow for execution...\n [ComfyUI] Received JSON with keys: ['prompt']\n [ComfyUI] Prompt has 4 nodes\n [ComfyUI] Node 1: LoadImage\n [ComfyUI] Inputs: {\"image\": \"image.png\"}\n [ComfyUI] Node 4: MaskPreview\n [ComfyUI] Inputs: {\"mask\": [\"26\", 0]}\n [ComfyUI] Node 12: LoadSAM3Model\n [ComfyUI] Inputs: {\"precision\": \"auto\", \"compile\": false}\n [ComfyUI] Node 26: SAM3InteractiveCollector\n [ComfyUI] Inputs: {\"multi_prompts_store\": \"[{\\\"positive_points\\\":[{\\\"x\\\":3348.288109906738,\\\"y\\\":2452.2208696844737}],\\\"negative_points\\\":[],\\\"positive_boxes\\\":[],\\\"negative_boxes\\\":[],\\\"name\\\":\\\"Prompt 1\\\"},{\\\"positiv\n [ComfyUI] Generated prompt_id: d3506526-5083-4c61-9bc4-43b3c786251a\n [ComfyUI] Calling execution.validate_prompt()...\n [ComfyUI] Validation result: valid=True\n [ComfyUI] === Validation PASSED ===\n [ComfyUI] got prompt\n [ComfyUI] [comfy-env] Running LoadSAM3Model: precision: 'auto', compile: False\n [ComfyUI] [ComfyUI-SAM3] python: /root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [VRAM] Before LoadSAM3Model: 567 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] sys_path sent to worker: ['/workspaces/SAM3-0918/ComfyUI', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3', '/root/.ce/.pixi/envs/sam3-nodes/lib/python3.12/site-packages', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3']\n [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSAM3Model.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'sam3-nodes', 'python', '/tmp/comfyui_pvenv_2f4orjtw/persistent_worker.py', 'abstract://comfy_worker_bc4edfd21732']...\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_bc4edfd21732 (abstract, no filesystem path)\n [ComfyUI] [ComfyUI-SAM3] Health check: failed\n [ComfyUI] [ComfyUI-SAM3] Socket unhealthy, restarting worker...\n [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload)\n Frame 2 saved (frame_001.jpg, t=2.3s)\n [capture-periodic] freeze=1ms shot=145ms unfreeze=3ms saved=True\n [ComfyUI] [worker:ComfyUI-SAM3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=14 sending call_method\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 269 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=15 sending model_to_device\n [ComfyUI] Model 'Sam3VideoInferenceWithInstanceInteractivity_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 269 / 7703 MB\n [ComfyUI] [comfy-env] LoadSAM3Model done (2.40s): result: NodeOutput\n [ComfyUI] [VRAM] After LoadSAM3Model: 269 / 7703 MB\n [ComfyUI] [comfy-env] Running SAM3InteractiveCollector: multi_prompts_store: '[{\"positive_points\":[{\"x\":3348.288109906738,\"y\":2452.220..., sam3_model_config: dict, image: torch.float32 [1,4480,6720,3] cpu, unique_id: '26'\n [ComfyUI] [VRAM] Before SAM3InteractiveCollector: 269 / 7703 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.sam3_interactive.SAM3InteractiveCollector.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'image' shape: torch.Size([1, 4480, 6720, 3])\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=16 sending call_method\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 4480, 6720, 3]\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 4480, 6720, 3])\n Frame 3 saved (frame_002.jpg, t=4.6s)\n [capture-periodic] freeze=1ms shot=150ms unfreeze=2ms saved=True\n [capture-loop] iter=50 t=5.7s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=6.1/31.3GB (19%) swap=0.7/32.0GB (2%) cpu=15% browser_rss=1.49GB\n [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=16\n [ComfyUI] [comfy-env] VRAM request: 1.84GB, free before eviction: 7.69GB\n [ComfyUI] [comfy-env] VRAM after eviction: 7.69GB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +405MB (now 405MB) reserved=416MB peak=405MB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +1373MB (now 1778MB) reserved=1792MB peak=1778MB\n [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=16\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +264MB (now 2042MB) reserved=2528MB peak=2476MB"
|
|
},
|
|
{
|
|
"file": "frame_004.jpg",
|
|
"time": 11.13,
|
|
"log": "Capturing execution frames: scene_seg_interactive.json\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 3895 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=13 sending model_to_device\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -303MB (now 3148MB) reserved=3520MB peak=5550MB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -1468MB (now 1680MB) reserved=3520MB peak=5550MB\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 567 / 7703 MB\n Frame 1 saved (frame_000.jpg, t=0.0s)\n Validating workflow...\n [ComfyUI] === /validate endpoint called ===\n Queuing workflow for execution...\n [ComfyUI] Received JSON with keys: ['prompt']\n [ComfyUI] Prompt has 4 nodes\n [ComfyUI] Node 1: LoadImage\n [ComfyUI] Inputs: {\"image\": \"image.png\"}\n [ComfyUI] Node 4: MaskPreview\n [ComfyUI] Inputs: {\"mask\": [\"26\", 0]}\n [ComfyUI] Node 12: LoadSAM3Model\n [ComfyUI] Inputs: {\"precision\": \"auto\", \"compile\": false}\n [ComfyUI] Node 26: SAM3InteractiveCollector\n [ComfyUI] Inputs: {\"multi_prompts_store\": \"[{\\\"positive_points\\\":[{\\\"x\\\":3348.288109906738,\\\"y\\\":2452.2208696844737}],\\\"negative_points\\\":[],\\\"positive_boxes\\\":[],\\\"negative_boxes\\\":[],\\\"name\\\":\\\"Prompt 1\\\"},{\\\"positiv\n [ComfyUI] Generated prompt_id: d3506526-5083-4c61-9bc4-43b3c786251a\n [ComfyUI] Calling execution.validate_prompt()...\n [ComfyUI] Validation result: valid=True\n [ComfyUI] === Validation PASSED ===\n [ComfyUI] got prompt\n [ComfyUI] [comfy-env] Running LoadSAM3Model: precision: 'auto', compile: False\n [ComfyUI] [ComfyUI-SAM3] python: /root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [VRAM] Before LoadSAM3Model: 567 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] sys_path sent to worker: ['/workspaces/SAM3-0918/ComfyUI', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3', '/root/.ce/.pixi/envs/sam3-nodes/lib/python3.12/site-packages', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3']\n [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSAM3Model.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'sam3-nodes', 'python', '/tmp/comfyui_pvenv_2f4orjtw/persistent_worker.py', 'abstract://comfy_worker_bc4edfd21732']...\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_bc4edfd21732 (abstract, no filesystem path)\n [ComfyUI] [ComfyUI-SAM3] Health check: failed\n [ComfyUI] [ComfyUI-SAM3] Socket unhealthy, restarting worker...\n [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload)\n Frame 2 saved (frame_001.jpg, t=2.3s)\n [capture-periodic] freeze=1ms shot=145ms unfreeze=3ms saved=True\n [ComfyUI] [worker:ComfyUI-SAM3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=14 sending call_method\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 269 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=15 sending model_to_device\n [ComfyUI] Model 'Sam3VideoInferenceWithInstanceInteractivity_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 269 / 7703 MB\n [ComfyUI] [comfy-env] LoadSAM3Model done (2.40s): result: NodeOutput\n [ComfyUI] [VRAM] After LoadSAM3Model: 269 / 7703 MB\n [ComfyUI] [comfy-env] Running SAM3InteractiveCollector: multi_prompts_store: '[{\"positive_points\":[{\"x\":3348.288109906738,\"y\":2452.220..., sam3_model_config: dict, image: torch.float32 [1,4480,6720,3] cpu, unique_id: '26'\n [ComfyUI] [VRAM] Before SAM3InteractiveCollector: 269 / 7703 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.sam3_interactive.SAM3InteractiveCollector.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'image' shape: torch.Size([1, 4480, 6720, 3])\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=16 sending call_method\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 4480, 6720, 3]\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 4480, 6720, 3])\n Frame 3 saved (frame_002.jpg, t=4.6s)\n [capture-periodic] freeze=1ms shot=150ms unfreeze=2ms saved=True\n [capture-loop] iter=50 t=5.7s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=6.1/31.3GB (19%) swap=0.7/32.0GB (2%) cpu=15% browser_rss=1.49GB\n [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=16\n [ComfyUI] [comfy-env] VRAM request: 1.84GB, free before eviction: 7.69GB\n [ComfyUI] [comfy-env] VRAM after eviction: 7.69GB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +405MB (now 405MB) reserved=416MB peak=405MB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +1373MB (now 1778MB) reserved=1792MB peak=1778MB\n [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=16\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +264MB (now 2042MB) reserved=2528MB peak=2476MB\n Frame 4 saved (frame_003.jpg, t=9.1s)\n [capture-periodic] freeze=2ms shot=152ms unfreeze=3ms saved=True\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] Created 1 model patchers: ['Sam3VideoInferenceWithInstanceInteractivity_1']\n [ComfyUI] [comfy-env] SAM3InteractiveCollector done (6.66s): result: NodeOutput\n [ComfyUI] [VRAM] After SAM3InteractiveCollector: 3991 / 7703 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (1756 MB)\n [ComfyUI] Prompt executed in 10.28 seconds\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (1756 MB) -> cpu: 3991 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=17 sending model_to_device\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -249MB (now 1794MB) reserved=3616MB peak=3220MB"
|
|
},
|
|
{
|
|
"file": "frame_005.jpg",
|
|
"time": 12.71,
|
|
"log": "Capturing execution frames: scene_seg_interactive.json\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 3895 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=13 sending model_to_device\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -303MB (now 3148MB) reserved=3520MB peak=5550MB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -1468MB (now 1680MB) reserved=3520MB peak=5550MB\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 567 / 7703 MB\n Frame 1 saved (frame_000.jpg, t=0.0s)\n Validating workflow...\n [ComfyUI] === /validate endpoint called ===\n Queuing workflow for execution...\n [ComfyUI] Received JSON with keys: ['prompt']\n [ComfyUI] Prompt has 4 nodes\n [ComfyUI] Node 1: LoadImage\n [ComfyUI] Inputs: {\"image\": \"image.png\"}\n [ComfyUI] Node 4: MaskPreview\n [ComfyUI] Inputs: {\"mask\": [\"26\", 0]}\n [ComfyUI] Node 12: LoadSAM3Model\n [ComfyUI] Inputs: {\"precision\": \"auto\", \"compile\": false}\n [ComfyUI] Node 26: SAM3InteractiveCollector\n [ComfyUI] Inputs: {\"multi_prompts_store\": \"[{\\\"positive_points\\\":[{\\\"x\\\":3348.288109906738,\\\"y\\\":2452.2208696844737}],\\\"negative_points\\\":[],\\\"positive_boxes\\\":[],\\\"negative_boxes\\\":[],\\\"name\\\":\\\"Prompt 1\\\"},{\\\"positiv\n [ComfyUI] Generated prompt_id: d3506526-5083-4c61-9bc4-43b3c786251a\n [ComfyUI] Calling execution.validate_prompt()...\n [ComfyUI] Validation result: valid=True\n [ComfyUI] === Validation PASSED ===\n [ComfyUI] got prompt\n [ComfyUI] [comfy-env] Running LoadSAM3Model: precision: 'auto', compile: False\n [ComfyUI] [ComfyUI-SAM3] python: /root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [VRAM] Before LoadSAM3Model: 567 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] sys_path sent to worker: ['/workspaces/SAM3-0918/ComfyUI', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3', '/root/.ce/.pixi/envs/sam3-nodes/lib/python3.12/site-packages', '/workspaces/SAM3-0918/ComfyUI/custom_nodes/ComfyUI-SAM3']\n [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSAM3Model.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/sam3-nodes/bin/python\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'sam3-nodes', 'python', '/tmp/comfyui_pvenv_2f4orjtw/persistent_worker.py', 'abstract://comfy_worker_bc4edfd21732']...\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_bc4edfd21732 (abstract, no filesystem path)\n [ComfyUI] [ComfyUI-SAM3] Health check: failed\n [ComfyUI] [ComfyUI-SAM3] Socket unhealthy, restarting worker...\n [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload)\n Frame 2 saved (frame_001.jpg, t=2.3s)\n [capture-periodic] freeze=1ms shot=145ms unfreeze=3ms saved=True\n [ComfyUI] [worker:ComfyUI-SAM3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=14 sending call_method\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 269 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=15 sending model_to_device\n [ComfyUI] Model 'Sam3VideoInferenceWithInstanceInteractivity_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 269 / 7703 MB\n [ComfyUI] [comfy-env] LoadSAM3Model done (2.40s): result: NodeOutput\n [ComfyUI] [VRAM] After LoadSAM3Model: 269 / 7703 MB\n [ComfyUI] [comfy-env] Running SAM3InteractiveCollector: multi_prompts_store: '[{\"positive_points\":[{\"x\":3348.288109906738,\"y\":2452.220..., sam3_model_config: dict, image: torch.float32 [1,4480,6720,3] cpu, unique_id: '26'\n [ComfyUI] [VRAM] Before SAM3InteractiveCollector: 269 / 7703 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.sam3_interactive.SAM3InteractiveCollector.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'image' shape: torch.Size([1, 4480, 6720, 3])\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=16 sending call_method\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 4480, 6720, 3]\n [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 4480, 6720, 3])\n Frame 3 saved (frame_002.jpg, t=4.6s)\n [capture-periodic] freeze=1ms shot=150ms unfreeze=2ms saved=True\n [capture-loop] iter=50 t=5.7s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=6.1/31.3GB (19%) swap=0.7/32.0GB (2%) cpu=15% browser_rss=1.49GB\n [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=16\n [ComfyUI] [comfy-env] VRAM request: 1.84GB, free before eviction: 7.69GB\n [ComfyUI] [comfy-env] VRAM after eviction: 7.69GB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +405MB (now 405MB) reserved=416MB peak=405MB\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +1373MB (now 1778MB) reserved=1792MB peak=1778MB\n [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=16\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +264MB (now 2042MB) reserved=2528MB peak=2476MB\n Frame 4 saved (frame_003.jpg, t=9.1s)\n [capture-periodic] freeze=2ms shot=152ms unfreeze=3ms saved=True\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] Created 1 model patchers: ['Sam3VideoInferenceWithInstanceInteractivity_1']\n [ComfyUI] [comfy-env] SAM3InteractiveCollector done (6.66s): result: NodeOutput\n [ComfyUI] [VRAM] After SAM3InteractiveCollector: 3991 / 7703 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (1756 MB)\n [ComfyUI] Prompt executed in 10.28 seconds\n [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (1756 MB) -> cpu: 3991 / 7703 MB\n [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-SAM3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=17 sending model_to_device\n [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] -249MB (now 1794MB) reserved=3616MB peak=3220MB\n Node executed (1 total), capturing...\n [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (1756 MB): 759 / 7703 MB\n Frame 5 saved (frame_004.jpg, t=11.1s)\n [capture-node] freeze=443ms shot=687ms unfreeze=8ms saved=True"
|
|
},
|
|
{
|
|
"file": "frame_006.jpg",
|
|
"time": 15.333049535751343,
|
|
"log": "Final screenshot"
|
|
}
|
|
],
|
|
"total_time": 12.96
|
|
} |