Capturing execution frames: image_seg_text.json [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (1756 MB) -> cpu: 2487 / 7703 MB [ComfyUI] [ComfyUI-SAM3] python: /root/.ce/.pixi/envs/sam3-nodes/bin/python [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-SAM3] sys_path sent to worker: ['/workspaces/SAM3-1009/ComfyUI', '/workspaces/SAM3-1009/ComfyUI/custom_nodes/ComfyUI-SAM3', '/root/.ce/.pixi/envs/sam3-nodes/lib/python3.12/site-packages', '/workspaces/SAM3-1009/ComfyUI/custom_nodes/ComfyUI-SAM3'] [ComfyUI] [ComfyUI-SAM3] Health check: failed [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/sam3-nodes/bin/python [ComfyUI] [ComfyUI-SAM3] Socket unhealthy, restarting worker... [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'sam3-nodes', 'python', '/tmp/comfyui_pvenv_y0czp7ta/persistent_worker.py', 'abstract://comfy_worker_69da4b410c5f']... [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_69da4b410c5f (abstract, no filesystem path) [ComfyUI] [worker:ComfyUI-SAM3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [ComfyUI] [SubprocessWorker] call_id=4 sending model_to_device [ComfyUI] Model 'Sam3VideoInferenceWithInstanceInteractivity_1' gone from worker (restarted?), treating as offloaded [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (1756 MB): 269 / 7703 MB Frame 1 saved (frame_000.jpg, t=0.0s) Validating workflow... [ComfyUI] === /validate endpoint called === Queuing workflow for execution... [ComfyUI] Received JSON with keys: ['prompt'] [ComfyUI] Prompt has 5 nodes [ComfyUI] Node 1: LoadImage [ComfyUI] Inputs: {"image": "example_image.jpg"} [ComfyUI] Node 3: PreviewImage [ComfyUI] Inputs: {"images": ["15", 1]} [ComfyUI] Node 4: MaskPreview [ComfyUI] Inputs: {"mask": ["15", 0]} [ComfyUI] Node 12: LoadSAM3Model [ComfyUI] Inputs: {"precision": "fp32", "compile": false} [ComfyUI] Node 15: SAM3Grounding [ComfyUI] Inputs: {"confidence_threshold": 0.2, "text_prompt": "child", "max_detections": -1, "sam3_model_config": ["12", 0], "image": ["1", 0]} [ComfyUI] Generated prompt_id: c9985b67-982e-4517-bf9f-03e2e6a03806 [ComfyUI] Calling execution.validate_prompt()... [ComfyUI] Validation result: valid=True [ComfyUI] === Validation PASSED === [ComfyUI] got prompt [ComfyUI] [comfy-env] Running LoadSAM3Model: precision: 'fp32', compile: False [ComfyUI] [VRAM] Before LoadSAM3Model: 269 / 7703 MB [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSAM3Model.EXECUTE_NORMALIZED [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-SAM3] Health check: ok [ComfyUI] [SubprocessWorker] worker started/confirmed [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [ComfyUI] [SubprocessWorker] created 0 shm blocks [ComfyUI] [SubprocessWorker] sending request via socket... [ComfyUI] [SubprocessWorker] call_id=5 sending call_method [ComfyUI] [SubprocessWorker] got response: ok [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (1756 MB) -> cpu: 269 / 7703 MB [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-SAM3] Health check: ok [ComfyUI] [SubprocessWorker] call_id=6 sending model_to_device [ComfyUI] Model 'Sam3VideoInferenceWithInstanceInteractivity_1' gone from worker (restarted?), treating as offloaded [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (1756 MB): 269 / 7703 MB [ComfyUI] [comfy-env] LoadSAM3Model done (0.27s): result: NodeOutput [ComfyUI] [VRAM] After LoadSAM3Model: 269 / 7703 MB [ComfyUI] [comfy-env] Running SAM3Grounding: confidence_threshold: 0.2, text_prompt: 'child', max_detections: -1, sam3_model_config: dict, image: torch.float32 [1,720,1280,3] cpu [ComfyUI] [VRAM] Before SAM3Grounding: 269 / 7703 MB [ComfyUI] [SubprocessWorker] call_method: nodes.segmentation.SAM3Grounding.EXECUTE_NORMALIZED [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-SAM3] Health check: ok [ComfyUI] [SubprocessWorker] worker started/confirmed [ComfyUI] [comfy-env] PRE-SERIALIZE 'image' shape: torch.Size([1, 720, 1280, 3]) [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [ComfyUI] [SubprocessWorker] created 0 shm blocks [ComfyUI] [SubprocessWorker] sending request via socket... [ComfyUI] [SubprocessWorker] call_id=7 sending call_method [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 720, 1280, 3] [ComfyUI] [worker:ComfyUI-SAM3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 720, 1280, 3]) [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=7 [ComfyUI] [comfy-env] VRAM request: 3.50GB, free before eviction: 7.69GB [ComfyUI] [comfy-env] VRAM after eviction: 7.69GB [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +748MB (now 748MB) reserved=768MB peak=748MB Frame 2 saved (frame_001.jpg, t=2.3s) [capture-periodic] freeze=2ms shot=112ms unfreeze=2ms saved=True [ComfyUI] [worker:ComfyUI-SAM3] WARNING: attention_flash cannot run on fp32 Q/K/V. Falling back to attention_pytorch with flash-SDPA disabled. [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +2703MB (now 3452MB) reserved=3776MB peak=3603MB [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] [VRAM] +252MB (now 3704MB) reserved=3936MB peak=3704MB [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention [ComfyUI] [worker:ComfyUI-SAM3] WARNING: Flash Attention failed, using default SDPA: Mask must not be set for Flash attention Frame 3 saved (frame_002.jpg, t=4.6s) [capture-periodic] freeze=1ms shot=134ms unfreeze=3ms saved=True [ComfyUI] [SubprocessWorker] got response: ok [ComfyUI] [comfy-env] Created 1 model patchers: ['Sam3VideoInferenceWithInstanceInteractivity_1'] [ComfyUI] [comfy-env] SAM3Grounding done (4.49s): result: NodeOutput [ComfyUI] [VRAM] After SAM3Grounding: 3961 / 7703 MB [ComfyUI] [VRAM] Loaded: SubprocessModel (3334 MB) Node executed (1 total), capturing... [ComfyUI] Prompt executed in 4.97 seconds [ComfyUI] [ComfyUI-SAM3] python: /root/.ce/.pixi/envs/sam3-nodes/bin/python [ComfyUI] [comfy-env] [VRAM] Before offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB) -> cpu: 3961 / 7703 MB [ComfyUI] [ComfyUI-SAM3] sys_path sent to worker: ['/workspaces/SAM3-1009/ComfyUI', '/workspaces/SAM3-1009/ComfyUI/custom_nodes/ComfyUI-SAM3', '/root/.ce/.pixi/envs/sam3-nodes/lib/python3.12/site-packages', '/workspaces/SAM3-1009/ComfyUI/custom_nodes/ComfyUI-SAM3'] [ComfyUI] [ComfyUI-SAM3] Health check: ping (timeout=5.0s)... [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/sam3-nodes/bin/python [ComfyUI] [ComfyUI-SAM3] Health check: failed [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'sam3-nodes', 'python', '/tmp/comfyui_pvenv_y0czp7ta/persistent_worker.py', 'abstract://comfy_worker_da80d14e809f']... [ComfyUI] [ComfyUI-SAM3] Socket unhealthy, restarting worker... [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_da80d14e809f (abstract, no filesystem path) [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) Frame 4 saved (frame_003.jpg, t=5.3s) [capture-node] freeze=2ms shot=132ms unfreeze=2ms saved=True Node executed (2 total), capturing... Frame 5 saved (frame_004.jpg, t=5.7s) [capture-node] freeze=2ms shot=152ms unfreeze=0ms saved=True Execution complete (t=5.7s) Captured 5 unique frames over 5.93s [debug] iframes: 0 [timing] trigger_3d_previews: 0.0s [ComfyUI] [worker:ComfyUI-SAM3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [ComfyUI] [SubprocessWorker] call_id=8 sending model_to_device [ComfyUI] Model 'Sam3VideoInferenceWithInstanceInteractivity_1' gone from worker (restarted?), treating as offloaded [ComfyUI] [comfy-env] [VRAM] After offload 'Sam3VideoInferenceWithInstanceInteractivity_1' (3334 MB): 269 / 7703 MB Saved high-quality screenshot: image_seg_text_executed.png [timing] final_screenshot: 0.3s Captured 6 video frames