[ComfyUI] [comfy-env] [VRAM] Before offload 'MoGeWrapper_1' (631 MB) -> cpu: 14073 / 24122 MB Capturing execution frames: sharp_basic.json [ComfyUI] [ComfyUI-MoGe2] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-MoGe2] python: /tmp/comfytest-home/.ce/.pixi/envs/moge2-nodes/bin/python [ComfyUI] [ComfyUI-MoGe2] sys_path sent to worker: ['/workspaces/Sharp-2211/ComfyUI', '/workspaces/Sharp-2211/ComfyUI/custom_nodes/ComfyUI-MoGe2', '/tmp/comfytest-home/.ce/.pixi/envs/moge2-nodes/lib/python3.1/site-packages', '/workspaces/Sharp-2211/ComfyUI/custom_nodes/ComfyUI-MoGe2'] [ComfyUI] [ComfyUI-MoGe2] Health check: failed [ComfyUI] [SubprocessWorker] is_pixi=True, python=/tmp/comfytest-home/.ce/.pixi/envs/moge2-nodes/bin/python [ComfyUI] [ComfyUI-MoGe2] Socket unhealthy, restarting worker... [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [ComfyUI] [SubprocessWorker] launching cmd=['/tmp/comfytest-home/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/tmp/comfytest-home/.ce/pixi.toml', '-e', 'moge2-nodes', 'python', '/tmp/comfyui_pvenv_ex649j74/persistent_worker.py', 'abstract://comfy_worker_252cdf4fa006']... [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_252cdf4fa006 (abstract, no filesystem path) [ComfyUI] [worker:ComfyUI-MoGe2] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [ComfyUI] [worker:ComfyUI-MoGe2] WARNING: comfy_kitchen does not support stochastic FP8 rounding, please update comfy_kitchen. [ComfyUI] [SubprocessWorker] call_id=3 sending model_to_device [ComfyUI] [WARNING] Model 'MoGeWrapper_1' gone from worker (restarted?), treating as offloaded [ComfyUI] [comfy-env] [VRAM] After offload 'MoGeWrapper_1' (631 MB): 14334 / 24122 MB [ComfyUI] [comfy-env] [VRAM] Before offload 'RGBGaussianPredictor_1' (2679 MB) -> cpu: 14334 / 24122 MB [ComfyUI] [ComfyUI-Sharp] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-Sharp] Health check: ok [ComfyUI] [SubprocessWorker] call_id=5 sending model_to_device [ComfyUI] [worker:ComfyUI-Sharp] [VRAM] -814MB (now 1874MB) reserved=7328MB peak=7062MB [ComfyUI] [worker:ComfyUI-Sharp] [VRAM] -1617MB (now 258MB) reserved=7328MB peak=7062MB [ComfyUI] [comfy-env] [VRAM] After offload 'RGBGaussianPredictor_1' (2679 MB): 7034 / 24122 MB [ComfyUI] [INFO] Using RAM pressure cache. Frame 1 saved (frame_000.jpg, t=0.0s) Validating workflow... [ComfyUI] [INFO] === /validate endpoint called === Queuing workflow for execution... [ComfyUI] [INFO] Received JSON with keys: ['prompt'] [ComfyUI] [INFO] Prompt has 4 nodes [ComfyUI] [INFO] Node 1: LoadImage [ComfyUI] [INFO] Inputs: {"image": "beach.jpg"} [ComfyUI] [INFO] Node 2: LoadSharpModel [ComfyUI] [INFO] Inputs: {"precision": "auto"} [ComfyUI] [INFO] Node 5: SharpPredict [ComfyUI] [INFO] Inputs: {"focal_length_mm": 30, "output_prefix": "sharp", "model": ["2", 0], "image": ["1", 0]} [ComfyUI] [INFO] Node 6: PreviewGaussianSharp [ComfyUI] [INFO] Inputs: {"preview_gaussian": "", "ply_path": ["5", 0], "extrinsics": ["5", 1], "intrinsics": ["5", 2]} [ComfyUI] [INFO] Generated prompt_id: cae6e76c-d568-492d-b085-7aa10b804d9e [ComfyUI] [INFO] Calling execution.validate_prompt()... [ComfyUI] [INFO] Validation result: valid=True [ComfyUI] [INFO] === Validation PASSED === [ComfyUI] [INFO] got prompt [ComfyUI] [comfy-env] Running LoadSharpModel: precision: 'auto' [ComfyUI] [ComfyUI-Sharp] python: /tmp/comfytest-home/.ce/.pixi/envs/sharp-nodes/bin/python [ComfyUI] [VRAM] Before LoadSharpModel: 4995 / 24122 MB [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSharpModel.EXECUTE_NORMALIZED [ComfyUI] [ComfyUI-Sharp] sys_path sent to worker: ['/workspaces/Sharp-2211/ComfyUI', '/workspaces/Sharp-2211/ComfyUI/custom_nodes/ComfyUI-Sharp', '/tmp/comfytest-home/.ce/.pixi/envs/sharp-nodes/lib/python3.1/site-packages', '/workspaces/Sharp-2211/ComfyUI/custom_nodes/ComfyUI-Sharp'] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/tmp/comfytest-home/.ce/.pixi/envs/sharp-nodes/bin/python [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [ComfyUI] [SubprocessWorker] launching cmd=['/tmp/comfytest-home/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/tmp/comfytest-home/.ce/pixi.toml', '-e', 'sharp-nodes', 'python', '/tmp/comfyui_pvenv_xcjd5ki2/persistent_worker.py', 'abstract://comfy_worker_398afb58be11']... [ComfyUI] [ComfyUI-Sharp] Health check: ping (timeout=5.0s)... [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_398afb58be11 (abstract, no filesystem path) [ComfyUI] [ComfyUI-Sharp] Health check: failed [ComfyUI] [ComfyUI-Sharp] Socket unhealthy, restarting worker... [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [ComfyUI] [worker:ComfyUI-Sharp] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [ComfyUI] [worker:ComfyUI-Sharp] WARNING: comfy_kitchen does not support stochastic FP8 rounding, please update comfy_kitchen. [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=6 sending call_method [ComfyUI] [worker:ComfyUI-Sharp] [LoadSharpModel] precision='auto' -> dtype=bf16 (device=cuda:0) [ComfyUI] [worker:ComfyUI-Sharp] [LoadSharpModel] checkpoint already present, reusing (no download): /workspaces/Sharp-2211/ComfyUI/models/sharp/sharp_2572gikvuh.pt (2679.6 MB) [ComfyUI] [worker:ComfyUI-Sharp] [LoadSharpModel] checkpoint ready: /workspaces/Sharp-2211/ComfyUI/models/sharp/sharp_2572gikvuh.pt (2679.6 MB) [ComfyUI] [worker:ComfyUI-Sharp] [LoadSharpModel] config: precision=auto -> dtype=bf16 [ComfyUI] [SubprocessWorker] got response: ok [ComfyUI] [comfy-env] [VRAM] Before offload 'RGBGaussianPredictor_1' (2679 MB) -> cpu: 4817 / 24122 MB [ComfyUI] [ComfyUI-Sharp] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-Sharp] Health check: ok [ComfyUI] [SubprocessWorker] call_id=7 sending model_to_device [ComfyUI] [WARNING] Model 'RGBGaussianPredictor_1' gone from worker (restarted?), treating as offloaded [ComfyUI] [comfy-env] [VRAM] After offload 'RGBGaussianPredictor_1' (2679 MB): 4817 / 24122 MB [ComfyUI] [comfy-env] [VRAM] Before offload 'MoGeWrapper_1' (631 MB) -> cpu: 4817 / 24122 MB [ComfyUI] [ComfyUI-MoGe2] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-MoGe2] Health check: ok [ComfyUI] [SubprocessWorker] call_id=4 sending model_to_device [ComfyUI] [WARNING] Model 'MoGeWrapper_1' gone from worker (restarted?), treating as offloaded [ComfyUI] [comfy-env] [VRAM] After offload 'MoGeWrapper_1' (631 MB): 4817 / 24122 MB [ComfyUI] [comfy-env] LoadSharpModel done (2.07s): result: NodeOutput [ComfyUI] [VRAM] After LoadSharpModel: 4817 / 24122 MB [ComfyUI] [comfy-env] Running SharpPredict: focal_length_mm: 30.0, output_prefix: 'sharp', model: dict, image: torch.float32 [1,1024,1536,3] cpu [ComfyUI] [VRAM] Before SharpPredict: 4817 / 24122 MB Frame 2 saved (frame_001.jpg, t=2.2s) [capture-periodic] freeze=1ms shot=118ms unfreeze=1ms saved=True [ComfyUI] [SubprocessWorker] call_method: nodes.predict.SharpPredict.EXECUTE_NORMALIZED [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [ComfyUI] [ComfyUI-Sharp] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-Sharp] Health check: ok [ComfyUI] [SubprocessWorker] worker started/confirmed [ComfyUI] [comfy-env] PRE-SERIALIZE 'image' shape: torch.Size([1, 1024, 1536, 3]) [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [ComfyUI] [SubprocessWorker] created 0 shm blocks [ComfyUI] [SubprocessWorker] sending request via socket... [ComfyUI] [SubprocessWorker] call_id=8 sending call_method [ComfyUI] [worker:ComfyUI-Sharp] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [ComfyUI] [worker:ComfyUI-Sharp] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 1024, 1536, 3] [ComfyUI] [worker:ComfyUI-Sharp] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 1024, 1536, 3]) Frame 3 saved (frame_002.jpg, t=4.5s) [capture-periodic] freeze=1ms shot=83ms unfreeze=1ms saved=True [ComfyUI] [worker:ComfyUI-Sharp] [LoadSharpModel] loading checkpoint from /workspaces/Sharp-2211/ComfyUI/models/sharp/sharp_2572gikvuh.pt (dtype=bf16) [capture-loop] iter=50 t=5.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=10.3/31.3GB (33%) swap=3.5/32.0GB (11%) cpu=34% browser_rss=0.86GB [ComfyUI] [worker:ComfyUI-Sharp] [LoadSharpModel] initializing model on meta device... [ComfyUI] [worker:ComfyUI-Sharp] [LoadSharpModel] model ready (torch.bfloat16) [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=8 [ComfyUI] [comfy-env] VRAM request: 2.81GB, free before eviction: 20.24GB [ComfyUI] [comfy-env] VRAM after eviction: 20.24GB [ComfyUI] [worker:ComfyUI-Sharp] [VRAM] +475MB (now 475MB) reserved=480MB peak=475MB [ComfyUI] [worker:ComfyUI-Sharp] [VRAM] +2767MB (now 3242MB) reserved=3456MB peak=3287MB [ComfyUI] [worker:ComfyUI-Sharp] [VRAM] +359MB (now 3601MB) reserved=3744MB peak=3601MB [ComfyUI] [worker:ComfyUI-Sharp] [VRAM] +562MB (now 4164MB) reserved=7840MB peak=7053MB [capture-loop] iter=100 t=10.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=1 ram=12.8/31.3GB (41%) swap=3.5/32.0GB (11%) cpu=14% browser_rss=0.74GB [ComfyUI] [worker:ComfyUI-Sharp] [VRAM] +234MB (now 4398MB) reserved=7360MB peak=7053MB [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=8 [ComfyUI] [SubprocessWorker] got response: ok [ComfyUI] [comfy-env] Created 1 model patchers: ['RGBGaussianPredictor_1'] [ComfyUI] [comfy-env] SharpPredict done (9.78s): result: NodeOutput [ComfyUI] [VRAM] After SharpPredict: 12291 / 24122 MB [ComfyUI] [VRAM] Loaded: SubprocessModel (2679 MB) [ComfyUI] [comfy-env] Running PreviewGaussianSharp: ply_path: '/workspaces/Sharp-2211/ComfyUI/output/sharp_178087128086..., extrinsics: list[4], intrinsics: list[3] [ComfyUI] [VRAM] Before PreviewGaussianSharp: 12291 / 24122 MB [ComfyUI] [VRAM] Loaded: SubprocessModel (2679 MB) [ComfyUI] [SubprocessWorker] call_method: nodes.preview_gaussian_sharp.PreviewGaussianSharp.EXECUTE_NORMALIZED [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [ComfyUI] [ComfyUI-GaussianPack] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-GaussianPack] 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=3 sending call_method [ComfyUI] [SubprocessWorker] got response: ok [ComfyUI] [comfy-env] PreviewGaussianSharp done (0.05s): result: NodeOutput [ComfyUI] [VRAM] After PreviewGaussianSharp: 12291 / 24122 MB [ComfyUI] [VRAM] Loaded: SubprocessModel (2679 MB) [ComfyUI] [INFO] Prompt executed in 11.96 seconds [ComfyUI] [comfy-env] [VRAM] Before offload 'RGBGaussianPredictor_1' (2679 MB) -> cpu: 12291 / 24122 MB [ComfyUI] [ComfyUI-Sharp] Health check: ping (timeout=5.0s)... [ComfyUI] [ComfyUI-Sharp] Health check: ok [ComfyUI] [SubprocessWorker] call_id=9 sending model_to_device Node executed (1 total), capturing... [ComfyUI] [worker:ComfyUI-Sharp] [VRAM] -2112MB (now 2287MB) reserved=7360MB peak=7053MB [ComfyUI] [worker:ComfyUI-Sharp] [VRAM] -1801MB (now 486MB) reserved=7360MB peak=7053MB Frame 4 saved (frame_003.jpg, t=12.4s) [capture-node] freeze=611ms shot=375ms unfreeze=0ms saved=True Execution complete (t=12.4s) [3d-wait] Phase 1: Waiting for 'Loading 3D Model' text to disappear... [3d-wait] Phase 1 done in 0.0s [3d-wait] Phase 2: iframes=1 [3d-wait] iframe viewer_ready=True (matched 1 console logs) [3d-wait] Unfrozen in 0.001s, rendering for 5s... [ComfyUI] [comfy-env] [VRAM] After offload 'RGBGaussianPredictor_1' (2679 MB): 5027 / 24122 MB [ComfyUI] [INFO] Using RAM pressure cache. [3d-wait] JS halted via CDP after 7.9s [3d-wait] Re-frozen in 31.6s [3d-wait] Total 3D wait: 31.6s Captured 4 unique frames over 45.05s [debug] iframes: 1 [debug] iframe[0]: src=http://127.0.0.1:41898/extensions/ComfyUI-GaussianPack/viewer_gaussian_sharp.htm, canvas=1536x1024, rafFrozen=True [timing] trigger_3d_previews: 0.0s Saved high-quality screenshot: sharp_basic_executed.png [timing] final_screenshot: 0.3s Captured 5 video frames