setup plugin alembic.autogenerate.schemas setup plugin alembic.autogenerate.tables setup plugin alembic.autogenerate.types setup plugin alembic.autogenerate.constraints setup plugin alembic.autogenerate.defaults setup plugin alembic.autogenerate.comments [comfy-env] ComfyUI-DepthAnythingV3: 1 isolation env(s): [comfy-env] nodes -> C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes [comfy-env] Workspace: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env [comfy-env] env: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes [OK] [comfy-env] prestartup complete [comfy-env] ComfyUI-GeometryPack: 1 isolation env(s): [comfy-env] nodes -> C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GeometryPack\nodes [comfy-env] env: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\geometrypack-nodes [OK] [comfy-env] prestartup complete Prestartup times for custom nodes: 0.2 seconds: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GeometryPack 0.4 seconds: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3 Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': "ImportError: No module named 'triton'", 'capabilities': []} Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4']} Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']} Checkpoint files will always be loaded safely. Total VRAM 12287 MB, total RAM 32648 MB pytorch version: 2.11.0+cu130 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 3060 : cudaMallocAsync Using async weight offloading with 2 streams Enabled pinned memory 13059.0 Using pytorch attention aimdo: src-win/cuda-detour.c:38:INFO:aimdo_setup_hooks: installing 6 hooks aimdo: src-win/cuda-detour.c:28:DEBUG:install_hook_entries: hooks successfully installed aimdo: src-win/shmem-detect.c:80:INFO:comfy-aimdo WDDM adapter match: NVIDIA GeForce RTX 3060 runtime_luid=00000000:0000b1f7 dxgi_luid=00000000:0000b1f7 aimdo: src/control.c:152:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 3060 (VRAM: 12287 MB) DynamicVRAM support detected and enabled Python version: 3.13.12 (tags/v3.13.12:1cbe481, Feb 3 2026, 18:22:25) [MSC v.1944 64 bit (AMD64)] ComfyUI version: 0.21.1 comfy-aimdo version: 0.3.0 comfy-kitchen version: 0.2.8 ****** User settings have been changed to be stored on the server instead of browser storage. ****** ****** For multi-user setups add the --multi-user CLI argument to enable multiple user profiles. ****** ComfyUI frontend version: 1.43.18 [Prompt Server] web root: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static Asset seeder disabled [comfy-env] Version: 0.3.89 [comfy-env] register_nodes: ComfyUI-DepthAnythingV3 [comfy-env] ComfyUI source dir: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI [comfy-env] Found 1 isolation env(s) [comfy-env] Scanning nodes metadata (isolation root)... [comfy-env] depthanythingv3-nodes: Library/bin has 237 DLLs [comfy-env] Metadata scan: C:\Users\ContainerAdministrator\.pixi\bin\pixi.exe run --as-is --manifest-path C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\pixi.toml -e depthanythingv3-nodes python C:\Users\ContainerAdministrator\AppData\Local\Temp\comfy_meta_kjl7k3x8.py C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3 nodes C:\Users\ContainerAdministrator\AppData\Local\Temp\comfy_meta_out_vaqet016.pkl [comfy-env] Scan env PATH for nodes: [comfy-env] [0] C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes [comfy-env] [1] C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Library\bin [comfy-env] [2] C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Scripts [comfy-env] [3] C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\bpy [comfy-env] [4] C:\Windows\System32 [comfy-env] [5] C:\Windows [comfy-env] [6] C:\Windows\System32\Wbem [comfy-env] Metadata scan stderr for nodes: [comfy-env] [meta-scan] importing nodes from C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3 [comfy-env] ERROR:root:Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [comfy-env] [meta-scan] import OK [comfy-env] Scanned nodes: 15 nodes (35.0s) [comfy-env] Scanned nodes root: 15 nodes (35.1s) [comfy-env] Imported nodes root: 15 nodes (isolation) [comfy-env] Registered 15 total nodes loading... calling register_nodes [comfy-env] Version: 0.3.89 [comfy-env] register_nodes: ComfyUI-GeometryPack [comfy-env] ComfyUI source dir: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI [comfy-env] Found 1 isolation env(s) [comfy-env] Scanning nodes metadata (isolation root)... [comfy-env] geometrypack-nodes: Library/bin has 613 DLLs [comfy-env] Metadata scan: C:\Users\ContainerAdministrator\.pixi\bin\pixi.exe run --as-is --manifest-path C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\pixi.toml -e geometrypack-nodes python C:\Users\ContainerAdministrator\AppData\Local\Temp\comfy_meta_cezrf4ng.py C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GeometryPack nodes C:\Users\ContainerAdministrator\AppData\Local\Temp\comfy_meta_out_7p80x_cx.pkl [comfy-env] Scan env PATH for nodes: [comfy-env] [0] C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\geometrypack-nodes [comfy-env] [1] C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\geometrypack-nodes\Library\bin [comfy-env] [2] C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\geometrypack-nodes\Scripts [comfy-env] [3] C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\geometrypack-nodes\Lib\site-packages\bpy [comfy-env] [4] C:\Windows\System32 [comfy-env] [5] C:\Windows [comfy-env] [6] C:\Windows\System32\Wbem [comfy-env] Metadata scan stderr for nodes: [comfy-env] [meta-scan] importing nodes from C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GeometryPack [comfy-env] ERROR:root:Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [comfy-env] [meta-scan] import OK [comfy-env] Scanned nodes: 125 nodes (17.2s) [comfy-env] Scanned nodes root: 125 nodes (17.3s) [comfy-env] Imported nodes root: 125 nodes (isolation) [comfy-env] Registered 125 total nodes Import times for custom nodes: 0.0 seconds: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py 0.0 seconds: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-validate-endpoint 0.3 seconds: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-KJNodes 2.5 seconds: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite 17.4 seconds: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GeometryPack 35.8 seconds: C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3 Context impl SQLiteImpl. Will assume non-transactional DDL. Context impl SQLiteImpl. Will assume non-transactional DDL. Running upgrade -> 0001_assets, Initial assets schema Revision ID: 0001_assets Revises: None Create Date: 2025-12-10 00:00:00 Running upgrade 0001_assets -> 0002_merge_to_asset_references, Merge AssetInfo and AssetCacheState into unified asset_references table. Running upgrade 0002_merge_to_asset_references -> 0003_add_metadata_job_id, Add system_metadata and job_id columns to asset_references. Change preview_id FK from assets.id to asset_references.id. Database upgraded from None to 0003_add_metadata_job_id Starting server To see the GUI go to: http://127.0.0.1:41888 [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version. === /validate endpoint called === Received JSON with keys: ['prompt'] Prompt has 11 nodes Node 2: LoadImage Inputs: {"image": "bridge.jpg"} Node 3: DownloadAndLoadDepthAnythingV3Model Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} Node 4: PreviewImage Inputs: {"images": ["12", 0]} Node 6: PreviewImage Inputs: {"images": ["12", 1]} Node 7: PreviewImage Inputs: {"images": ["12", 2]} Node 8: PreviewImage Inputs: {"images": ["12", 3]} Node 9: PreviewAny Inputs: {"source": ["12", 6]} Node 10: PreviewAny Inputs: {"source": ["12", 5]} Node 11: MaskPreview Inputs: {"mask": ["12", 7]} Node 12: DepthAnything_V3 Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} Node 13: PreviewImage Inputs: {"images": ["12", 4]} Generated prompt_id: ee40efb2-36af-459e-9cd8-342b65d5ba2d Calling execution.validate_prompt()... Validation result: valid=True === Validation PASSED === got prompt [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [comfy-env] SubprocessWorker: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [comfy-env] env_vars: {'COMFYUI_BASE': 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI'} [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [comfy-env] depthanythingv3-nodes: Library/bin has 237 DLLs [ComfyUI-DepthAnythingV3] python: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\.pixi\\envs\\depthanythingv3-nodes\\Lib\\site-packages', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3'] [SubprocessWorker] is_pixi=True, python=C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [SubprocessWorker] launching cmd=['C:\\Users\\ContainerAdministrator\\.pixi\\bin\\pixi.exe', 'run', '--as-is', '--manifest-path', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\pixi.toml', '-e', 'depthanythingv3-nodes', 'python', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Temp\\comfyui_pvenv_50_ji_ox\\persistent_worker.py', 'tcp://127.0.0.1:62726']... [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=1 sending call_method model.safetensors: 0%| | 0.00/1.64G [00:00 cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=3 sending model_to_device [worker:ComfyUI-DepthAnythingV3] [VRAM] -335MB (now 511MB) reserved=2464MB peak=1502MB [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB === /validate endpoint called === Received JSON with keys: ['prompt'] Prompt has 6 nodes Node 2: LoadImage Inputs: {"image": "kaffi.jpg"} Node 3: DownloadAndLoadDepthAnythingV3Model Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} Node 21: DepthAnything_V3 Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} Node 22: DA3_ToPointCloud Inputs: {"confidence_threshold": 0.2, "downsample": 1, "allow_around_1": 1, "filter_outliers": false, "outlier_percentage": 5, "depth_raw": ["21", 0], "confidence": ["21", 1], "intrinsics": ["21", 6], "sky_ma Node 23: DA3_SavePointCloud Inputs: {"filename_prefix": "pointcloud", "pointcloud": ["22", 0]} Node 25: DA3_PreviewPointCloud Inputs: {"file_path": ["23", 0], "color_mode": "RGB", "preview_vtk": ""} Generated prompt_id: 42414277-bee9-414b-8c7d-5750f58acb67 Calling execution.validate_prompt()... Validation result: valid=True === Validation PASSED === got prompt [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: failed [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [comfy-env] depthanythingv3-nodes: Library/bin has 237 DLLs [ComfyUI-DepthAnythingV3] python: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\.pixi\\envs\\depthanythingv3-nodes\\Lib\\site-packages', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3'] [SubprocessWorker] is_pixi=True, python=C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [SubprocessWorker] launching cmd=['C:\\Users\\ContainerAdministrator\\.pixi\\bin\\pixi.exe', 'run', '--as-is', '--manifest-path', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\pixi.toml', '-e', 'depthanythingv3-nodes', 'python', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Temp\\comfyui_pvenv_50_ji_ox\\persistent_worker.py', 'tcp://127.0.0.1:65435']... [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=4 sending call_method [SubprocessWorker] got response: ok [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=5 sending model_to_device Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB [comfy-env] DownloadAndLoadDepthAnythingV3Model done (4.11s): result: NodeOutput [VRAM] After DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [comfy-env] Running DepthAnything_V3: normalization_mode: 'Raw', resize_method: 'resize', invert_depth: False, keep_model_size: False, da3_model: dict, images: torch.float32 [1,533,800,3] cpu [VRAM] Before DepthAnything_V3: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 533, 800, 3]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=6 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 533, 800, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 533, 800, 3]) [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [SubprocessWorker] callback 'request_vram_budget' from call_id=6 [comfy-env] VRAM request: 0.82GB, free before eviction: 11.79GB [comfy-env] VRAM after eviction: 11.79GB [worker:ComfyUI-DepthAnythingV3] [VRAM] +330MB (now 330MB) reserved=352MB peak=330MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +692MB (now 1022MB) reserved=1152MB peak=1022MB [SubprocessWorker] callback 'report_progress' from call_id=6 [SubprocessWorker] got response: ok [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [comfy-env] DepthAnything_V3 done (6.74s): result: NodeOutput [VRAM] After DepthAnything_V3: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_ToPointCloud: confidence_threshold: 0.2, downsample: 1, allow_around_1: True, filter_outliers: False, outlier_percentage: 5.0, depth_raw: torch.float32 [1,532,800,3] cpu, confidence: torch.float32 [1,532,800,3] cpu, intrinsics: '{\n "intrinsics": [\n {\n "image_0": [\n ..., sky_mask: torch.float32 [1,532,800] cpu, source_image: torch.float32 [1,532,800,3] cpu [VRAM] Before DA3_ToPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.nodes_3d.DA3_ToPointCloud.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'depth_raw' shape: torch.Size([1, 532, 800, 3]) [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 532, 800, 3]) [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 532, 800]) [comfy-env] PRE-SERIALIZE 'source_image' shape: torch.Size([1, 532, 800, 3]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=7 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [SubprocessWorker] got response: ok [comfy-env] DA3_ToPointCloud done (0.15s): result: NodeOutput [VRAM] After DA3_ToPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [VRAM] Before DA3_SavePointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=8 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[310964, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([310964, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[310964] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([310964]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[310964, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([310964, 3]) [worker:ComfyUI-DepthAnythingV3] [VRAM] -230MB (now 792MB) reserved=1888MB peak=1022MB [SubprocessWorker] got response: ok [comfy-env] DA3_SavePointCloud done (5.12s): result: NodeOutput [VRAM] After DA3_SavePointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_PreviewPointCloud: file_path: 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\..., color_mode: 'RGB' [VRAM] Before DA3_PreviewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=9 sending call_method [SubprocessWorker] got response: ok [comfy-env] DA3_PreviewPointCloud done (0.04s): result: NodeOutput [VRAM] After DA3_PreviewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) Prompt executed in 16.19 seconds [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=10 sending model_to_device [worker:ComfyUI-DepthAnythingV3] [VRAM] -250MB (now 543MB) reserved=1888MB peak=1022MB [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB === /validate endpoint called === Received JSON with keys: ['prompt'] Prompt has 8 nodes Node 3: DownloadAndLoadDepthAnythingV3Model Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} Node 21: LoadImageDataSetFromFolder Inputs: {"folder": "SOH"} Node 27: PreviewImage Inputs: {"images": ["21", 0]} Node 38: DA3_MultiViewPointCloud Inputs: {"extrinsics": ["39", 4], "intrinsics": ["39", 5], "confidence_threshold": 0.3, "downsample": 4, "use_icp": false, "allow_around_1": false, "filter_outliers": true, "outlier_percentage": 5, "depths": Node 39: DepthAnythingV3_MultiView Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["21", 0]} Node 44: DA3_SavePointCloud Inputs: {"filename_prefix": "pointcloud", "pointcloud": ["38", 0]} Node 45: PreviewAny Inputs: {"source": ["44", 0]} Node 48: DA3_PreviewPointCloud Inputs: {"file_path": ["44", 0], "color_mode": "RGB", "preview_vtk": ""} Generated prompt_id: 67a153c8-9077-45f2-bd6e-ad41235ebf98 Calling execution.validate_prompt()... Validation result: valid=True === Validation PASSED === got prompt [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: failed [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [comfy-env] depthanythingv3-nodes: Library/bin has 237 DLLs [ComfyUI-DepthAnythingV3] python: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\.pixi\\envs\\depthanythingv3-nodes\\Lib\\site-packages', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3'] [SubprocessWorker] is_pixi=True, python=C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [SubprocessWorker] launching cmd=['C:\\Users\\ContainerAdministrator\\.pixi\\bin\\pixi.exe', 'run', '--as-is', '--manifest-path', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\pixi.toml', '-e', 'depthanythingv3-nodes', 'python', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Temp\\comfyui_pvenv_50_ji_ox\\persistent_worker.py', 'tcp://127.0.0.1:60456']... [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=11 sending call_method [SubprocessWorker] got response: ok [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=12 sending model_to_device Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB [comfy-env] DownloadAndLoadDepthAnythingV3Model done (4.02s): result: NodeOutput [VRAM] After DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [comfy-env] Running DepthAnythingV3_MultiView: normalization_mode: 'Raw', resize_method: 'resize', invert_depth: False, keep_model_size: False, da3_model: dict, images: torch.float32 [1,680,1208,3] cpu [VRAM] Before DepthAnythingV3_MultiView: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=13 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [SubprocessWorker] callback 'request_vram_budget' from call_id=13 [comfy-env] VRAM request: 0.82GB, free before eviction: 11.79GB [comfy-env] VRAM after eviction: 11.79GB [worker:ComfyUI-DepthAnythingV3] [VRAM] +338MB (now 338MB) reserved=352MB peak=338MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +820MB (now 1159MB) reserved=1344MB peak=1159MB [SubprocessWorker] got response: ok [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [comfy-env] DepthAnythingV3_MultiView done (7.04s): result: NodeOutput [VRAM] After DepthAnythingV3_MultiView: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DepthAnythingV3_MultiView: normalization_mode: 'Raw', resize_method: 'resize', invert_depth: False, keep_model_size: False, da3_model: dict, images: torch.float32 [1,680,1208,3] cpu [VRAM] Before DepthAnythingV3_MultiView: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=14 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [SubprocessWorker] callback 'request_vram_budget' from call_id=14 [comfy-env] VRAM request: 0.82GB, free before eviction: 11.79GB [comfy-env] VRAM after eviction: 11.79GB [worker:ComfyUI-DepthAnythingV3] [VRAM] -216MB (now 943MB) reserved=2784MB peak=1628MB [SubprocessWorker] got response: ok [comfy-env] DepthAnythingV3_MultiView done (0.85s): result: NodeOutput [VRAM] After DepthAnythingV3_MultiView: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_MultiViewPointCloud: extrinsics: '{\n "extrinsics": [\n {\n "image_0": [\n ..., intrinsics: '{\n "intrinsics": [\n {\n "image_0": [\n ..., confidence_threshold: 0.3, downsample: 4, use_icp: False, allow_around_1: False, filter_outliers: True, outlier_percentage: 5.0, depths: torch.float32 [1,680,1208,3] cpu, images: torch.float32 [1,680,1208,3] cpu, confidence: torch.float32 [1,680,1208,3] cpu, sky_mask: torch.float32 [1,680,1208] cpu [VRAM] Before DA3_MultiViewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.nodes_multiview.DA3_MultiViewPointCloud.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'depths' shape: torch.Size([1, 680, 1208, 3]) [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 680, 1208, 3]) [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 680, 1208]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=15 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208]) [SubprocessWorker] callback 'report_progress' from call_id=15 [SubprocessWorker] got response: ok [comfy-env] DA3_MultiViewPointCloud done (0.15s): result: NodeOutput [VRAM] After DA3_MultiViewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_MultiViewPointCloud: extrinsics: '{\n "extrinsics": [\n {\n "image_0": [\n ..., intrinsics: '{\n "intrinsics": [\n {\n "image_0": [\n ..., confidence_threshold: 0.3, downsample: 4, use_icp: False, allow_around_1: False, filter_outliers: True, outlier_percentage: 5.0, depths: torch.float32 [1,680,1208,3] cpu, images: torch.float32 [1,680,1208,3] cpu, confidence: torch.float32 [1,680,1208,3] cpu, sky_mask: torch.float32 [1,680,1208] cpu [VRAM] Before DA3_MultiViewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.nodes_multiview.DA3_MultiViewPointCloud.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'depths' shape: torch.Size([1, 680, 1208, 3]) [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 680, 1208, 3]) [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 680, 1208]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=16 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208]) [SubprocessWorker] callback 'report_progress' from call_id=16 [SubprocessWorker] got response: ok [comfy-env] DA3_MultiViewPointCloud done (0.14s): result: NodeOutput [VRAM] After DA3_MultiViewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [VRAM] Before DA3_SavePointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=17 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18826, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18826, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18826, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18826, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18826] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18826]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18826] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18826]) [SubprocessWorker] got response: ok [comfy-env] DA3_SavePointCloud done (0.48s): result: NodeOutput [VRAM] After DA3_SavePointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [VRAM] Before DA3_SavePointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=18 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20434, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20434, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20434, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20434, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20434] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20434]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20434] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20434]) [SubprocessWorker] got response: ok [comfy-env] DA3_SavePointCloud done (0.46s): result: NodeOutput [VRAM] After DA3_SavePointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_PreviewPointCloud: file_path: 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\..., color_mode: 'RGB' [VRAM] Before DA3_PreviewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=19 sending call_method [SubprocessWorker] got response: ok [comfy-env] DA3_PreviewPointCloud done (0.04s): result: NodeOutput [VRAM] After DA3_PreviewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_PreviewPointCloud: file_path: 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\..., color_mode: 'RGB' [VRAM] Before DA3_PreviewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=20 sending call_method [SubprocessWorker] got response: ok [comfy-env] DA3_PreviewPointCloud done (0.04s): result: NodeOutput [VRAM] After DA3_PreviewPointCloud: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) Prompt executed in 13.42 seconds [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=21 sending model_to_device [worker:ComfyUI-DepthAnythingV3] [VRAM] -281MB (now 663MB) reserved=2784MB peak=1628MB [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB === /validate endpoint called === Received JSON with keys: ['prompt'] Prompt has 6 nodes Node 2: LoadImage Inputs: {"image": "bas_relief.png"} Node 3: DownloadAndLoadDepthAnythingV3Model Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} Node 21: DepthAnything_V3 Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": true, "da3_model": ["3", 0], "images": ["2", 0]} Node 27: PreviewImage Inputs: {"images": ["21", 2]} Node 30: Preview3D Inputs: {"model_file": ["32", 0], "image": ""} Node 32: DA3_ToMesh Inputs: {"confidence_threshold": 0.1, "depth_edge_threshold": 0.1, "downsample": 1, "target_faces": 100000, "filename_prefix": "mesh", "allow_around_1": true, "use_draco_compression": false, "depth_raw": ["21 Generated prompt_id: ca8207f7-f59d-42f6-9336-4fa1e3489f21 Calling execution.validate_prompt()... Validation result: valid=True === Validation PASSED === got prompt [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: failed [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [comfy-env] depthanythingv3-nodes: Library/bin has 237 DLLs [ComfyUI-DepthAnythingV3] python: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\.pixi\\envs\\depthanythingv3-nodes\\Lib\\site-packages', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3'] [SubprocessWorker] is_pixi=True, python=C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [SubprocessWorker] launching cmd=['C:\\Users\\ContainerAdministrator\\.pixi\\bin\\pixi.exe', 'run', '--as-is', '--manifest-path', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\pixi.toml', '-e', 'depthanythingv3-nodes', 'python', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Temp\\comfyui_pvenv_50_ji_ox\\persistent_worker.py', 'tcp://127.0.0.1:63911']... [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=22 sending call_method [SubprocessWorker] got response: ok [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=23 sending model_to_device Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB [comfy-env] DownloadAndLoadDepthAnythingV3Model done (4.03s): result: NodeOutput [VRAM] After DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [comfy-env] Running DepthAnything_V3: normalization_mode: 'Raw', resize_method: 'resize', invert_depth: False, keep_model_size: True, da3_model: dict, images: torch.float32 [1,2000,1336,3] cpu [VRAM] Before DepthAnything_V3: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 2000, 1336, 3]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=24 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2000, 1336, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2000, 1336, 3]) [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [SubprocessWorker] callback 'request_vram_budget' from call_id=24 [comfy-env] VRAM request: 0.82GB, free before eviction: 11.79GB [comfy-env] VRAM after eviction: 11.79GB [worker:ComfyUI-DepthAnythingV3] [VRAM] +338MB (now 338MB) reserved=352MB peak=338MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +656MB (now 994MB) reserved=1248MB peak=994MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +932MB (now 1926MB) reserved=2368MB peak=1926MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -647MB (now 1279MB) reserved=7072MB peak=3435MB [SubprocessWorker] callback 'report_progress' from call_id=24 [SubprocessWorker] got response: ok [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [comfy-env] DepthAnything_V3 done (8.71s): result: NodeOutput [VRAM] After DepthAnything_V3: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [comfy-env] Running DA3_ToMesh: confidence_threshold: 0.1, depth_edge_threshold: 0.1, downsample: 1, target_faces: 100000, filename_prefix: 'mesh', allow_around_1: True, use_draco_compression: False, depth_raw: torch.float32 [1,2002,1330,3] cpu, confidence: torch.float32 [1,2002,1330,3] cpu, intrinsics: '{\n "intrinsics": [\n {\n "image_0": [\n ..., sky_mask: torch.float32 [1,2002,1330] cpu, source_image: torch.float32 [1,2002,1330,3] cpu [VRAM] Before DA3_ToMesh: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) [SubprocessWorker] call_method: nodes.nodes_3d.DA3_ToMesh.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'depth_raw' shape: torch.Size([1, 2002, 1330, 3]) [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 2002, 1330, 3]) [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 2002, 1330]) [comfy-env] PRE-SERIALIZE 'source_image' shape: torch.Size([1, 2002, 1330, 3]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=25 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330, 3]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330]) [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330, 3]) [worker:ComfyUI-DepthAnythingV3] WARNING: pyfqmr not installed, skipping decimation. Install with: pip install pyfqmr [worker:ComfyUI-DepthAnythingV3] [VRAM] -414MB (now 866MB) reserved=7072MB peak=3435MB [worker:ComfyUI-DepthAnythingV3] WARNING: pygltflib is required for material post-processing. Install with: pip install pygltflib. Mesh may appear dark or single-sided. [SubprocessWorker] got response: ok [comfy-env] DA3_ToMesh done (6.94s): result: NodeOutput [VRAM] After DA3_ToMesh: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) Prompt executed in 20.15 seconds [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=26 sending model_to_device [worker:ComfyUI-DepthAnythingV3] [VRAM] -260MB (now 607MB) reserved=7072MB peak=3435MB [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB === /validate endpoint called === Received JSON with keys: ['prompt'] Prompt has 5 nodes Node 2: DownloadAndLoadDepthAnythingV3Model Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} Node 3: LoadVideo Inputs: {"file": "robot_unitree.mp4", "video-preview": ""} Node 4: SaveVideo Inputs: {"filename_prefix": "video/preview_da3", "format": "auto", "codec": "auto", "video": ["6", 0]} Node 5: LoadSALADModel Inputs: {} Node 6: DepthAnythingV3_Streaming Inputs: {"normalization_mode": "Standard", "chunk_size": 30, "overlap": 8, "align_lib": "auto", "align_method": "sim3", "resize_method": "resize", "invert_depth": true, "save_pointcloud": false, "sample_ratio Generated prompt_id: e09bbc4c-c99d-4a9c-8069-5efc98917701 Calling execution.validate_prompt()... Validation result: valid=True === Validation PASSED === got prompt [comfy-env] Running LoadSALADModel: [VRAM] Before LoadSALADModel: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.load_model.LoadSALADModel.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: failed [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [comfy-env] depthanythingv3-nodes: Library/bin has 237 DLLs [ComfyUI-DepthAnythingV3] python: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\.pixi\\envs\\depthanythingv3-nodes\\Lib\\site-packages', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3'] [SubprocessWorker] is_pixi=True, python=C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [SubprocessWorker] launching cmd=['C:\\Users\\ContainerAdministrator\\.pixi\\bin\\pixi.exe', 'run', '--as-is', '--manifest-path', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\pixi.toml', '-e', 'depthanythingv3-nodes', 'python', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Temp\\comfyui_pvenv_50_ji_ox\\persistent_worker.py', 'tcp://127.0.0.1:54820']... [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [SubprocessWorker] worker started/confirmed [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=27 sending call_method Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. [worker:ComfyUI-DepthAnythingV3] WARNING: Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. dino_salad.safetensors: 0%| | 0.00/352M [00:00 cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=28 sending model_to_device Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB [comfy-env] LoadSALADModel done (9.38s): result: NodeOutput [VRAM] After LoadSALADModel: 1042 / 12287 MB [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=29 sending call_method [SubprocessWorker] got response: ok [comfy-env] DownloadAndLoadDepthAnythingV3Model done (0.08s): result: NodeOutput [VRAM] After DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [comfy-env] Running DepthAnythingV3_Streaming: normalization_mode: 'Standard', chunk_size: 30, overlap: 8, align_lib: 'auto', align_method: 'sim3', resize_method: 'resize', invert_depth: True, save_pointcloud: False, sample_ratio: 0.015, conf_threshold_coef: 0.75, da3_model: dict, video: VideoFromFile, salad_model: dict [VRAM] Before DepthAnythingV3_Streaming: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.streaming.node.DepthAnythingV3_Streaming.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 1 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=30 sending call_method [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [SubprocessWorker] callback 'request_vram_budget' from call_id=30 [comfy-env] VRAM request: 1.17GB, free before eviction: 11.79GB [comfy-env] VRAM after eviction: 11.79GB [worker:ComfyUI-DepthAnythingV3] [VRAM] +297MB (now 297MB) reserved=320MB peak=297MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +822MB (now 1119MB) reserved=1120MB peak=1119MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +277MB (now 1396MB) reserved=1408MB peak=1396MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +1063MB (now 2460MB) reserved=3936MB peak=2460MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +526MB (now 2986MB) reserved=4000MB peak=2986MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4928MB peak=3337MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4928MB peak=3688MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +372MB (now 4061MB) reserved=5728MB peak=4061MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +542MB (now 4603MB) reserved=5728MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -306MB (now 4298MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4504MB) reserved=5728MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -2988MB (now 1517MB) reserved=7136MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +943MB (now 2460MB) reserved=4000MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +526MB (now 2986MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] === WATCHDOG TICK 1 === [worker:ComfyUI-DepthAnythingV3] Thread 0x00002e7c (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 363 in wait File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 660 in wait File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\tqdm\_monitor.py", line 60 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Thread 0x0000150c (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 106 in _vram_poller File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 995 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Current thread 0x00003558 (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 52 in _watchdog File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 995 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Thread 0x00001e30 (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\cuda\memory.py", line 224 in empty_cache File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 1412 in _forward_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 1379 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 1591 in _process_depth_head File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 1577 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\pipeline.py", line 330 in _process_chunk File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\pipeline.py", line 277 in run File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\node.py", line 249 in execute File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\comfy_api\latest\_io.py", line 1833 in EXECUTE_NORMALIZED File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 1762 in main File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 1807 in [worker:ComfyUI-DepthAnythingV3] === END === [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5504MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7168MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +943MB (now 2460MB) reserved=4000MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +526MB (now 2986MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5504MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7168MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +943MB (now 2460MB) reserved=4000MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +526MB (now 2986MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5504MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7168MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +943MB (now 2460MB) reserved=4000MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +526MB (now 2986MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] === WATCHDOG TICK 2 === [worker:ComfyUI-DepthAnythingV3] Thread 0x00002e7c (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 363 in wait File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 660 in wait File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\tqdm\_monitor.py", line 60 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Thread 0x0000150c (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 106 in _vram_poller File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 995 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Current thread 0x00003558 (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 52 in _watchdog File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 995 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Thread 0x00001e30 (most recent call first): File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 329 in _apply_1d_rope File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 343 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 445 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 516 in attn_residual_func File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 521 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 791 in process_attention File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 750 in _get_intermediate_layers_not_chunked File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 800 in get_intermediate_layers File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 891 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 1560 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\pipeline.py", line 330 in _process_chunk File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\pipeline.py", line 277 in run File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\node.py", line 249 in execute File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\comfy_api\latest\_io.py", line 1833 in EXECUTE_NORMALIZED File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 1762 in main File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 1807 in [worker:ComfyUI-DepthAnythingV3] === END === [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5504MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7168MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +943MB (now 2460MB) reserved=4000MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +526MB (now 2986MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +701MB (now 4039MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -702MB (now 3337MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5504MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7168MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +943MB (now 2460MB) reserved=4000MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +526MB (now 2986MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4544MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4768MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +582MB (now 4270MB) reserved=5568MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +203MB (now 4473MB) reserved=5600MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -2957MB (now 1517MB) reserved=7168MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +499MB (now 2016MB) reserved=3040MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 2367MB) reserved=3040MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +233MB (now 2601MB) reserved=3296MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +233MB (now 2834MB) reserved=3520MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] === WATCHDOG TICK 3 === [worker:ComfyUI-DepthAnythingV3] Thread 0x00002e7c (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 363 in wait File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 660 in wait File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\tqdm\_monitor.py", line 60 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Thread 0x0000150c (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 106 in _vram_poller File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 995 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Current thread 0x00003558 (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 52 in _watchdog File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 995 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Thread 0x00001e30 (most recent call first): File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 338 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 445 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 516 in attn_residual_func File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 521 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 791 in process_attention File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 750 in _get_intermediate_layers_not_chunked File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 800 in get_intermediate_layers File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 891 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\depth_anything_v3\model.py", line 1560 in forward File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1790 in _call_impl File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\torch\nn\modules\module.py", line 1779 in _wrapped_call_impl File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\pipeline.py", line 330 in _process_chunk File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\pipeline.py", line 277 in run File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\node.py", line 249 in execute File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\comfy_api\latest\_io.py", line 1833 in EXECUTE_NORMALIZED File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 1762 in main File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 1807 in [worker:ComfyUI-DepthAnythingV3] === END === [worker:ComfyUI-DepthAnythingV3] [VRAM] +452MB (now 3287MB) reserved=3456MB peak=4603MB [worker:ComfyUI-DepthAnythingV3] [VRAM] -1901MB (now 1387MB) reserved=5536MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] -259MB (now 1128MB) reserved=1184MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [SubprocessWorker] callback 'report_progress' from call_id=30 [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +334MB (now 1462MB) reserved=1568MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] -335MB (now 1128MB) reserved=1568MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] +343MB (now 1472MB) reserved=1568MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] [VRAM] -344MB (now 1128MB) reserved=1568MB peak=4603MB [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] WARNING: faiss not installed, skipping loop closure. pip install faiss-cpu [SubprocessWorker] callback 'report_progress' from call_id=30 [worker:ComfyUI-DepthAnythingV3] === WATCHDOG TICK 4 === [worker:ComfyUI-DepthAnythingV3] Thread 0x00002e7c (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 363 in wait File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 660 in wait File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\tqdm\_monitor.py", line 60 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Thread 0x0000150c (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 106 in _vram_poller File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 995 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Current thread 0x00003558 (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 52 in _watchdog File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 995 in run File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1044 in _bootstrap_inner File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\threading.py", line 1015 in _bootstrap Thread 0x00001e30 (most recent call first): File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\zipfile\__init__.py", line 1266 in write File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\numpy\lib\_format_impl.py", line 777 in write_array File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\numpy\lib\_npyio_impl.py", line 786 in _savez File "C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\Lib\site-packages\numpy\lib\_npyio_impl.py", line 753 in savez_compressed File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3\nodes\streaming\node.py", line 271 in execute File "C:\workspaces\DepthAnythingV3-1430\portable-comfyui\ComfyUI_windows_portable\ComfyUI\comfy_api\latest\_io.py", line 1833 in EXECUTE_NORMALIZED File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 1762 in main File "C:\Users\ContainerAdministrator\AppData\Local\Temp\comfyui_pvenv_50_ji_ox\persistent_worker.py", line 1807 in [worker:ComfyUI-DepthAnythingV3] === END === [SubprocessWorker] got response: ok [comfy-env] Created 2 model patchers: ['DepthAnything3Net_1', 'VPRModel_2'] [comfy-env] DepthAnythingV3_Streaming done (248.27s): result: NodeOutput [VRAM] After DepthAnythingV3_Streaming: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (335 MB), SubprocessModel (783 MB) Prompt executed in 263.15 seconds [comfy-env] [VRAM] Before offload 'VPRModel_2' (335 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=31 sending model_to_device [worker:ComfyUI-DepthAnythingV3] [VRAM] -273MB (now 856MB) reserved=1568MB peak=4603MB [comfy-env] [VRAM] After offload 'VPRModel_2' (335 MB): 1042 / 12287 MB [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=32 sending model_to_device [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB === /validate endpoint called === Received JSON with keys: ['prompt'] Prompt has 4 nodes Node 2: LoadImage Inputs: {"image": "bridge.jpg"} Node 3: DownloadAndLoadDepthAnythingV3Model Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} Node 4: PreviewImage Inputs: {"images": ["14", 0]} Node 14: DepthAnything_V3 Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": true, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} Generated prompt_id: d08542b2-2a94-4984-a669-90130e4246b4 Calling execution.validate_prompt()... Validation result: valid=True === Validation PASSED === got prompt [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: failed [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [comfy-env] Invalidated 2 stale model patchers (will be cleaned up during next unload) [comfy-env] depthanythingv3-nodes: Library/bin has 237 DLLs [ComfyUI-DepthAnythingV3] python: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\.pixi\\envs\\depthanythingv3-nodes\\Lib\\site-packages', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3'] [SubprocessWorker] is_pixi=True, python=C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [SubprocessWorker] launching cmd=['C:\\Users\\ContainerAdministrator\\.pixi\\bin\\pixi.exe', 'run', '--as-is', '--manifest-path', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\pixi.toml', '-e', 'depthanythingv3-nodes', 'python', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Temp\\comfyui_pvenv_50_ji_ox\\persistent_worker.py', 'tcp://127.0.0.1:50386']... [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=33 sending call_method [SubprocessWorker] got response: ok [comfy-env] [VRAM] Before offload 'VPRModel_2' (335 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=34 sending model_to_device Model 'VPRModel_2' gone from worker (restarted?), treating as offloaded [comfy-env] [VRAM] After offload 'VPRModel_2' (335 MB): 1042 / 12287 MB [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=35 sending model_to_device Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB [comfy-env] DownloadAndLoadDepthAnythingV3Model done (4.19s): result: NodeOutput [VRAM] After DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [comfy-env] Running DepthAnything_V3: normalization_mode: 'V2-Style', resize_method: 'resize', invert_depth: True, keep_model_size: False, da3_model: dict, images: torch.float32 [1,683,1024,3] cpu [VRAM] Before DepthAnything_V3: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 683, 1024, 3]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=36 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 683, 1024, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 683, 1024, 3]) [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [SubprocessWorker] callback 'request_vram_budget' from call_id=36 [comfy-env] VRAM request: 0.82GB, free before eviction: 11.79GB [comfy-env] VRAM after eviction: 11.79GB [worker:ComfyUI-DepthAnythingV3] [VRAM] +266MB (now 266MB) reserved=288MB peak=266MB [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: This model does not support sky segmentation. V2-Style normalization will work but without sky masking. Use Mono/Metric/Nested models for best V2-Style results. [worker:ComfyUI-DepthAnythingV3] [VRAM] +825MB (now 1091MB) reserved=1280MB peak=1091MB [SubprocessWorker] callback 'report_progress' from call_id=36 [SubprocessWorker] got response: ok [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [comfy-env] DepthAnything_V3 done (7.09s): result: NodeOutput [VRAM] After DepthAnything_V3: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (783 MB) Prompt executed in 11.37 seconds [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=37 sending model_to_device [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB === /validate endpoint called === Received JSON with keys: ['prompt'] Prompt has 9 nodes Node 3: DownloadAndLoadDepthAnythingV3Model Inputs: {"model": "da3_base.safetensors", "precision": "auto", "attention": "auto"} Node 52: CreateVideo Inputs: {"fps": 10, "images": ["62", 0]} Node 53: CreateVideo Inputs: {"fps": 10, "images": ["61", 0]} Node 54: SaveVideo Inputs: {"filename_prefix": "video/ComfyUI", "format": "auto", "codec": "auto", "video": ["52", 0]} Node 55: SaveVideo Inputs: {"filename_prefix": "video/ComfyUI", "format": "auto", "codec": "auto", "video": ["53", 0]} Node 61: DepthAnything_V3 Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["71", 0]} Node 62: DepthAnythingV3_MultiView Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["71", 0]} Node 66: PreviewImage Inputs: {"images": ["71", 0]} Node 71: LoadImagesFromFolderKJ Inputs: {"folder": "input/robotframes", "width": 1024, "height": 576, "keep_aspect_ratio": "crop", "image_load_cap": 0, "start_index": 0, "include_subfolders": false} Generated prompt_id: 0e1ee0fe-c197-44f0-84ca-7a45360fbefd Calling execution.validate_prompt()... Validation result: valid=True === Validation PASSED === got prompt [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_base.safetensors', precision: 'auto', attention: 'auto' [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: failed [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [comfy-env] depthanythingv3-nodes: Library/bin has 237 DLLs [ComfyUI-DepthAnythingV3] python: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\.pixi\\envs\\depthanythingv3-nodes\\Lib\\site-packages', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3'] [SubprocessWorker] is_pixi=True, python=C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [SubprocessWorker] launching cmd=['C:\\Users\\ContainerAdministrator\\.pixi\\bin\\pixi.exe', 'run', '--as-is', '--manifest-path', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\pixi.toml', '-e', 'depthanythingv3-nodes', 'python', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Temp\\comfyui_pvenv_50_ji_ox\\persistent_worker.py', 'tcp://127.0.0.1:61510']... [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [SubprocessWorker] worker started/confirmed [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=38 sending call_method model.safetensors: 0%| | 0.00/542M [00:00 cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=39 sending model_to_device Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 1042 / 12287 MB [comfy-env] DownloadAndLoadDepthAnythingV3Model done (10.52s): result: NodeOutput [VRAM] After DownloadAndLoadDepthAnythingV3Model: 1042 / 12287 MB [comfy-env] Running DepthAnythingV3_MultiView: normalization_mode: 'V2-Style', resize_method: 'resize', invert_depth: False, keep_model_size: False, da3_model: dict, images: torch.float32 [13,576,1024,3] cpu [VRAM] Before DepthAnythingV3_MultiView: 1042 / 12287 MB [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([13, 576, 1024, 3]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=40 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[13, 576, 1024, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([13, 576, 1024, 3]) [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [SubprocessWorker] callback 'request_vram_budget' from call_id=40 [comfy-env] VRAM request: 0.27GB, free before eviction: 11.79GB [comfy-env] VRAM after eviction: 11.79GB [worker:ComfyUI-DepthAnythingV3] [VRAM] +254MB (now 254MB) reserved=256MB peak=254MB [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: This model does not support sky segmentation. V2-Style normalization will work but without sky masking. Use Mono/Metric/Nested models for best V2-Style results. [worker:ComfyUI-DepthAnythingV3] [VRAM] +627MB (now 882MB) reserved=1216MB peak=882MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +379MB (now 1261MB) reserved=1632MB peak=1261MB [worker:ComfyUI-DepthAnythingV3] [VRAM] +398MB (now 1659MB) reserved=2560MB peak=1752MB [SubprocessWorker] got response: ok [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [comfy-env] DepthAnythingV3_MultiView done (9.05s): result: NodeOutput [VRAM] After DepthAnythingV3_MultiView: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (258 MB) [comfy-env] Running DepthAnything_V3: normalization_mode: 'V2-Style', resize_method: 'resize', invert_depth: False, keep_model_size: False, da3_model: dict, images: torch.float32 [13,576,1024,3] cpu [VRAM] Before DepthAnything_V3: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (258 MB) [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [SubprocessWorker] acquired lock, ensuring started... [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: failed [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [comfy-env] depthanythingv3-nodes: Library/bin has 237 DLLs [ComfyUI-DepthAnythingV3] python: C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\.pixi\\envs\\depthanythingv3-nodes\\Lib\\site-packages', 'C:\\workspaces\\DepthAnythingV3-1430\\portable-comfyui\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-DepthAnythingV3'] [SubprocessWorker] is_pixi=True, python=C:\Users\ContainerAdministrator\AppData\Local\Programs\comfy-env\.pixi\envs\depthanythingv3-nodes\python.exe [SubprocessWorker] launching cmd=['C:\\Users\\ContainerAdministrator\\.pixi\\bin\\pixi.exe', 'run', '--as-is', '--manifest-path', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Programs\\comfy-env\\pixi.toml', '-e', 'depthanythingv3-nodes', 'python', 'C:\\Users\\ContainerAdministrator\\AppData\\Local\\Temp\\comfyui_pvenv_50_ji_ox\\persistent_worker.py', 'tcp://127.0.0.1:61524']... [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [SubprocessWorker] worker started/confirmed [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([13, 576, 1024, 3]) [SubprocessWorker] serializing kwargs to shm... [SubprocessWorker] created 0 shm blocks [SubprocessWorker] sending request via socket... [SubprocessWorker] call_id=41 sending call_method [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'manager_path', 'storage_key', 'storage_size'] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[13, 576, 1024, 3] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([13, 576, 1024, 3]) [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [SubprocessWorker] callback 'request_vram_budget' from call_id=41 [comfy-env] VRAM request: 0.27GB, free before eviction: 11.79GB [comfy-env] VRAM after eviction: 11.79GB [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: This model does not support sky segmentation. V2-Style normalization will work but without sky masking. Use Mono/Metric/Nested models for best V2-Style results. [worker:ComfyUI-DepthAnythingV3] [VRAM] +258MB (now 258MB) reserved=288MB peak=258MB [SubprocessWorker] callback 'report_progress' from call_id=41 [worker:ComfyUI-DepthAnythingV3] [VRAM] +598MB (now 856MB) reserved=1088MB peak=856MB [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [worker:ComfyUI-DepthAnythingV3] [VRAM] -556MB (now 301MB) reserved=1088MB peak=856MB [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] callback 'report_progress' from call_id=41 [SubprocessWorker] got response: ok [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (258 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=42 sending model_to_device [worker:ComfyUI-DepthAnythingV3] [VRAM] -226MB (now 75MB) reserved=1120MB peak=856MB [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (258 MB): 1042 / 12287 MB [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [comfy-env] DepthAnything_V3 done (13.00s): result: NodeOutput [VRAM] After DepthAnything_V3: 1042 / 12287 MB [VRAM] Loaded: SubprocessModel (258 MB) Prompt executed in 34.58 seconds [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (258 MB) -> cpu: 1042 / 12287 MB [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [ComfyUI-DepthAnythingV3] Health check: ok [SubprocessWorker] call_id=43 sending model_to_device [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (258 MB): 1042 / 12287 MB