[00:00] Crash dump logging enabled: /logs/DepthAnythingV3-1418/dev/linux-gpu/crash_dump.log [00:00] [00:00] [1/5] SYNTAX [00:00] ---------------------------------------- [00:00] [DEBUG] server=None, server_url=None, api=None [00:00] Found pyproject.toml (modern format) [00:00] Found requirements.txt (legacy format) [00:00] Unicode check: OK (all characters cp1252-safe) [00:00] Forbidden patterns check: OK [00:00] [SYNTAX] PASSED [00:00] [00:00] [2/5] INSTALL [00:00] ---------------------------------------- [00:00] [DEBUG] server=None, server_url=None, api=None [00:00] Setting up ComfyUI... [00:00] Creating virtual environment... [00:00] Running: uv venv /workspaces/DepthAnythingV3-1418/.venv --python 3.12 [00:00] Cloning ComfyUI (latest)... [00:00] Running: git clone --depth 1 https://github.com/comfyanonymous/ComfyUI.git /workspaces/DepthAnythingV3-1418/ComfyUI [00:02] Installing ComfyUI requirements... [00:02] Running: uv pip install --python /workspaces/DepthAnythingV3-1418/.venv/bin/python --index-url https://download.pytorch.org/whl/cu128 --extra-index-url https://pypi.org/simple --index-strategy unsafe-best-match -r /workspaces/DepthAnythingV3-1418/ComfyUI/requirements.txt [02:25] Installing custom node... [02:25] Copying ComfyUI-DepthAnythingV3 to custom_nodes/... [02:25] Installing node requirements... [02:25] Running: uv pip install --python /workspaces/DepthAnythingV3-1418/.venv/bin/python --index-url https://download.pytorch.org/whl/cu128 --extra-index-url https://pypi.org/simple --index-strategy unsafe-best-match -r /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/requirements.txt [02:27] Running install.py... [02:27] Running: /workspaces/DepthAnythingV3-1418/.venv/bin/python /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/install.py [02:28] [02:28] Installing 3 node dependencies... [02:28] Cloning ComfyUI-VideoHelperSuite... [02:28] Installing requirements for ComfyUI-VideoHelperSuite... [02:31] Cloning ComfyUI-KJNodes... [02:33] Installing requirements for ComfyUI-KJNodes... [02:35] Cloning ComfyUI-GeometryPack... [02:39] Installing requirements for ComfyUI-GeometryPack... [02:40] Running install.py for ComfyUI-GeometryPack... [02:42] [comfy-env] Workspace: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce [02:42] [comfy-env] ComfyUI: /workspaces/DepthAnythingV3-1418/ComfyUI [02:42] [comfy-env] Found 2 node config(s): [02:42] - depthanythingv3-nodes <- custom_nodes/ComfyUI-DepthAnythingV3/nodes/comfy-env.toml (python=host) [02:42] - geometrypack-nodes <- custom_nodes/ComfyUI-GeometryPack/nodes/comfy-env.toml (python=host) [02:42] [comfy-env] Bootstrap interpreter has python 3.12 + torch 2.11.0 (cu128). Looking for cuda-only wheels matching cu128/torch2.11/cp312. [02:42] [comfy-env] GPU: Detection: smi [02:42] Driver: 580.126.20 [02:42] CUDA: 13.0 [02:42] Recommended: CUDA 13.0 [02:42] [02:42] GPU 0: NVIDIA GeForce RTX 3090 (sm_86) [Ampere] 24576MB [02:42] [comfy-env] Comfyui feature -> torch 2.11.0 from https://download.pytorch.org/whl/cu128 (CUDA 12.8 via bootstrap torch) [02:42] [comfy-env] cuda-wheels: 3 package(s) need a matched (cuda, torch, python) combo: ['flash_attn', 'sageattention', 'cumesh'] [02:42] [comfy-env] cuda-wheels tier 1 (bootstrap): probing cu12.8/torch2.11/cp312 [02:42] [cuda-wheels] Looking up flash_attn: cu128 torch2.11 cp312 manylinux linux [02:43] [cuda-wheels] https://pozzettiandrea.github.io/cuda-wheels/v2/flash_attn/: HTTPError: HTTP Error 404: Not Found [02:43] [cuda-wheels] Found: flash_attn-2.8.3+cu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [02:43] [cuda-wheels] Looking up sageattention: cu128 torch2.11 cp312 manylinux linux [02:43] [cuda-wheels] Found: sageattention-2.2.0+cu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [02:43] [cuda-wheels] Looking up cumesh: cu128 torch2.11 cp312 manylinux linux [02:43] [cuda-wheels] Found: cumesh-0.0.1+cu128torch2.11-cp312-cp312-manylinux_2_35_x86_64.whl [02:43] [comfy-env] cuda-wheels combo: cu12.8/torch2.11 (bootstrap matches; per-node envs will pin to this) [02:43] [comfy-env] Root conda deps from ComfyUI-DepthAnythingV3: ['av', 'ffmpeg'] [02:43] [comfy-env] Root conda deps from ComfyUI-GeometryPack: ['av', 'ffmpeg'] [02:43] [comfy-env] Comfyui feature pin: torch ==2.11.0, torchvision ==0.26.*, torchaudio ==2.11.* [02:43] [comfy-env] Host glibc 2.35 -> comfyui feature system-requirements [02:43] [comfy-env] Root conda deps: ['av', 'ffmpeg'] [02:43] [comfy-env] comfyui312: python 3.12, torch from https://download.pytorch.org/whl/cu128 [02:43] [comfy-env] cuda-wheels combo: per-node cuda features will pin ['torch', 'torchaudio', 'torchvision'] via pypi-options.dependency-overrides (https://download.pytorch.org/whl/cu128) [02:43] [cuda-wheels] Looking up flash_attn: cu128 torch2.11 cp312 manylinux linux [02:43] [cuda-wheels] https://pozzettiandrea.github.io/cuda-wheels/v2/flash_attn/: HTTPError: HTTP Error 404: Not Found [02:43] [cuda-wheels] Found: flash_attn-2.8.3+cu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [02:43] [cuda-wheels] Looking up sageattention: cu128 torch2.11 cp312 manylinux linux [02:43] [cuda-wheels] Found: sageattention-2.2.0+cu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [02:43] [comfy-env] depthanythingv3-nodes: cuda-wheels deferred for post-pixi install (flash_attn, sageattention) [02:43] [comfy-env] depthanythingv3-nodes: torch override -> torch==2.11.0, torchvision==0.26.*, torchaudio==2.11.* from https://download.pytorch.org/whl/cu128 [02:43] [cuda-wheels] Looking up cumesh: cu128 torch2.11 cp312 manylinux linux [02:43] [cuda-wheels] Found: cumesh-0.0.1+cu128torch2.11-cp312-cp312-manylinux_2_35_x86_64.whl [02:43] [comfy-env] geometrypack-nodes: cuda-wheels deferred for post-pixi install (cumesh) [02:43] [comfy-env] geometrypack-nodes: torch override -> torch==2.11.0, torchvision==0.26.*, torchaudio==2.11.* from https://download.pytorch.org/whl/cu128 [02:43] Generated /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml [02:43] [comfy-env] Installing 2 environment(s): [02:43] - depthanythingv3-nodes (python=host, 9 pypi deps, 2 cuda wheels) [02:43] - geometrypack-nodes (python=host, 13 pypi deps, 1 cuda wheels) [02:43] [comfy-env] Running `pixi install --all`... [03:08] WARN Skipped running the post-link scripts because `run-post-link-scripts` = `false` [03:08] - bin/.librsvg-pre-unlink.sh [03:08] To enable them, run: [03:08] pixi config set --local run-post-link-scripts insecure [03:08] More info: [03:08] https://pixi.sh/latest/reference/pixi_configuration/#run-post-link-scripts [03:11] WARN Skipped running the post-link scripts because `run-post-link-scripts` = `false` [03:11] - bin/.librsvg-pre-unlink.sh [03:11] To enable them, run: [03:11] pixi config set --local run-post-link-scripts insecure [03:11] More info: [03:11] https://pixi.sh/latest/reference/pixi_configuration/#run-post-link-scripts [03:13] WARN Skipped running the post-link scripts because `run-post-link-scripts` = `false` [03:13] - bin/.librsvg-pre-unlink.sh [03:13] To enable them, run: [03:13] pixi config set --local run-post-link-scripts insecure [03:13] More info: [03:13] https://pixi.sh/latest/reference/pixi_configuration/#run-post-link-scripts [04:29] The following environments have been installed: default, comfyui, depthanythingv3-nodes, geometrypack-nodes. [04:29] [comfy-env] Note: env `default` is on disk but no node declares it in this run. Leaving as-is. Remove via `pixi clean --environment default` if intended. [04:29] [comfy-env] depthanythingv3-nodes: installing cuda-wheels with --no-deps (flash_attn, sageattention) [04:29] Using Python 3.12.13 environment at: .pixi/envs/depthanythingv3-nodes [04:31] Resolved 2 packages in 2.04s [04:31] Downloading sageattention (53.2MiB) [04:31] Downloading flash-attn (242.3MiB) [04:33] Downloaded sageattention [04:39] Downloaded flash-attn [04:39] Prepared 2 packages in 7.52s [04:39] Installed 2 packages in 10ms [04:39] + flash-attn==2.8.3+cu128torch2.11 (from https://github.com/PozzettiAndrea/cuda-wheels/releases/download/flash_attn-latest/flash_attn-2.8.3%2Bcu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl) [04:39] + sageattention==2.2.0+cu128torch2.11 (from https://github.com/PozzettiAndrea/cuda-wheels/releases/download/sageattention-latest/sageattention-2.2.0%2Bcu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl) [04:39] [comfy-env] geometrypack-nodes: installing cuda-wheels with --no-deps (cumesh) [04:39] Using Python 3.12.13 environment at: .pixi/envs/geometrypack-nodes [04:40] Resolved 1 package in 905ms [04:40] Downloading cumesh (19.5MiB) [04:40] Downloaded cumesh [04:40] Prepared 1 package in 424ms [04:40] Installed 1 package in 7ms [04:40] + cumesh==0.0.1+cu128torch2.11 (from https://github.com/PozzettiAndrea/cuda-wheels/releases/download/cumesh-latest/cumesh-0.0.1%2Bcu128torch2.11-cp312-cp312-manylinux_2_35_x86_64.whl) [04:40] [comfy-env] Install log: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/install.log [04:40] [04:40] Installation complete! [04:40] [04:40] [requirements] Re-installing main package requirements... [04:41] Installing requirements for ComfyUI-DepthAnythingV3... [04:41] [comfy-env] Workspace: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce [04:41] [comfy-env] ComfyUI: /workspaces/DepthAnythingV3-1418/ComfyUI [04:41] [comfy-env] Found 2 node config(s): [04:41] - depthanythingv3-nodes <- custom_nodes/ComfyUI-DepthAnythingV3/nodes/comfy-env.toml (python=host) [04:41] - geometrypack-nodes <- custom_nodes/ComfyUI-GeometryPack/nodes/comfy-env.toml (python=host) [04:41] [comfy-env] Bootstrap interpreter has python 3.12 + torch 2.11.0 (cu128). Looking for cuda-only wheels matching cu128/torch2.11/cp312. [04:41] [comfy-env] GPU: Detection: smi [04:41] Driver: 580.126.20 [04:41] CUDA: 13.0 [04:41] Recommended: CUDA 13.0 [04:41] [04:41] GPU 0: NVIDIA GeForce RTX 3090 (sm_86) [Ampere] 24576MB [04:41] [comfy-env] Comfyui feature -> torch 2.11.0 from https://download.pytorch.org/whl/cu128 (CUDA 12.8 via bootstrap torch) [04:41] [comfy-env] cuda-wheels: 3 package(s) need a matched (cuda, torch, python) combo: ['flash_attn', 'sageattention', 'cumesh'] [04:41] [comfy-env] cuda-wheels tier 1 (bootstrap): probing cu12.8/torch2.11/cp312 [04:41] [cuda-wheels] Looking up flash_attn: cu128 torch2.11 cp312 manylinux linux [04:41] [cuda-wheels] https://pozzettiandrea.github.io/cuda-wheels/v2/flash_attn/: HTTPError: HTTP Error 404: Not Found [04:41] [cuda-wheels] Found: flash_attn-2.8.3+cu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [04:41] [cuda-wheels] Looking up sageattention: cu128 torch2.11 cp312 manylinux linux [04:41] [cuda-wheels] Found: sageattention-2.2.0+cu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [04:41] [cuda-wheels] Looking up cumesh: cu128 torch2.11 cp312 manylinux linux [04:41] [cuda-wheels] Found: cumesh-0.0.1+cu128torch2.11-cp312-cp312-manylinux_2_35_x86_64.whl [04:41] [comfy-env] cuda-wheels combo: cu12.8/torch2.11 (bootstrap matches; per-node envs will pin to this) [04:41] [comfy-env] Root conda deps from ComfyUI-DepthAnythingV3: ['av', 'ffmpeg'] [04:41] [comfy-env] Root conda deps from ComfyUI-GeometryPack: ['av', 'ffmpeg'] [04:41] [comfy-env] Comfyui feature pin: torch ==2.11.0, torchvision ==0.26.*, torchaudio ==2.11.* [04:41] [comfy-env] Host glibc 2.35 -> comfyui feature system-requirements [04:41] [comfy-env] Root conda deps: ['av', 'ffmpeg'] [04:41] [comfy-env] comfyui312: python 3.12, torch from https://download.pytorch.org/whl/cu128 [04:41] [comfy-env] cuda-wheels combo: per-node cuda features will pin ['torch', 'torchaudio', 'torchvision'] via pypi-options.dependency-overrides (https://download.pytorch.org/whl/cu128) [04:41] [cuda-wheels] Looking up flash_attn: cu128 torch2.11 cp312 manylinux linux [04:41] [cuda-wheels] https://pozzettiandrea.github.io/cuda-wheels/v2/flash_attn/: HTTPError: HTTP Error 404: Not Found [04:42] [cuda-wheels] Found: flash_attn-2.8.3+cu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [04:42] [cuda-wheels] Looking up sageattention: cu128 torch2.11 cp312 manylinux linux [04:42] [cuda-wheels] Found: sageattention-2.2.0+cu128torch2.11-cp312-cp312-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [04:42] [comfy-env] depthanythingv3-nodes: cuda-wheels deferred for post-pixi install (flash_attn, sageattention) [04:42] [comfy-env] depthanythingv3-nodes: torch override -> torch==2.11.0, torchvision==0.26.*, torchaudio==2.11.* from https://download.pytorch.org/whl/cu128 [04:42] [cuda-wheels] Looking up cumesh: cu128 torch2.11 cp312 manylinux linux [04:42] [cuda-wheels] Found: cumesh-0.0.1+cu128torch2.11-cp312-cp312-manylinux_2_35_x86_64.whl [04:42] [comfy-env] geometrypack-nodes: cuda-wheels deferred for post-pixi install (cumesh) [04:42] [comfy-env] geometrypack-nodes: torch override -> torch==2.11.0, torchvision==0.26.*, torchaudio==2.11.* from https://download.pytorch.org/whl/cu128 [04:42] Generated /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml [04:42] [comfy-env] Installing 2 environment(s): [04:42] - depthanythingv3-nodes (python=host, 9 pypi deps, 2 cuda wheels) [04:42] - geometrypack-nodes (python=host, 13 pypi deps, 1 cuda wheels) [04:42] [comfy-env] Running `pixi install --all`... [04:42] The following environments have been installed: default, comfyui, depthanythingv3-nodes, geometrypack-nodes. [04:42] [comfy-env] Note: env `default` is on disk but no node declares it in this run. Leaving as-is. Remove via `pixi clean --environment default` if intended. [04:42] [comfy-env] depthanythingv3-nodes: installing cuda-wheels with --no-deps (flash_attn, sageattention) [04:42] Using Python 3.12.13 environment at: .pixi/envs/depthanythingv3-nodes [04:42] Checked 2 packages in 67ms [04:42] [comfy-env] geometrypack-nodes: installing cuda-wheels with --no-deps (cumesh) [04:42] Using Python 3.12.13 environment at: .pixi/envs/geometrypack-nodes [04:42] Checked 1 package in 89ms [04:42] [comfy-env] Install log: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/install.log [04:42] [04:42] Installation complete! [04:42] Installing 3 node dependency(ies)... [04:42] ComfyUI-VideoHelperSuite from Kosinkadink/ComfyUI-VideoHelperSuite [04:42] ComfyUI-VideoHelperSuite already exists, skipping... [04:42] ComfyUI-KJNodes from kijai/ComfyUI-KJNodes [04:42] ComfyUI-KJNodes already exists, skipping... [04:42] ComfyUI-GeometryPack from PozzettiAndrea/ComfyUI-GeometryPack [04:42] ComfyUI-GeometryPack already exists, skipping... [04:42] Installing validation endpoint... [04:42] Cloning PozzettiAndrea/ComfyUI-validate-endpoint... [04:42] Running: git clone --depth 1 https://github.com/PozzettiAndrea/ComfyUI-validate-endpoint.git /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-validate-endpoint [04:43] CUDA packages installed (no mock): flash_attn, sageattention [04:43] [INSTALL] PASSED [04:43] [04:43] [3/5] REGISTRATION [04:43] ---------------------------------------- [04:43] [DEBUG] server=None, server_url=None, api=None [04:43] Starting ComfyUI server... [04:43] Starting ComfyUI server on port 41890... [04:43] Starting ComfyUI server on port 41890... [04:43] Waiting for server to be ready (timeout: 600s)... [04:44] [ComfyUI] setup plugin alembic.autogenerate.schemas [04:44] [ComfyUI] setup plugin alembic.autogenerate.tables [04:44] [ComfyUI] setup plugin alembic.autogenerate.types [04:44] [ComfyUI] setup plugin alembic.autogenerate.constraints [04:44] [ComfyUI] setup plugin alembic.autogenerate.defaults [04:44] [ComfyUI] setup plugin alembic.autogenerate.comments [04:45] [ComfyUI] [comfy-env] ComfyUI-DepthAnythingV3: 1 isolation env(s): [04:45] [ComfyUI] [comfy-env] nodes -> /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes [04:45] [ComfyUI] [comfy-env] prestartup complete [04:45] [ComfyUI] [comfy-env] ComfyUI-GeometryPack: 1 isolation env(s): [04:45] [ComfyUI] [comfy-env] nodes -> /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-GeometryPack/nodes [04:45] [ComfyUI] [comfy-env] prestartup complete [04:45] [ComfyUI] [04:45] [ComfyUI] Prestartup times for custom nodes: [04:45] [ComfyUI] 0.1 seconds: /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-GeometryPack [04:45] [ComfyUI] 0.2 seconds: /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 [04:45] [ComfyUI] [04:51] [ComfyUI] WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [04:51] [ComfyUI] Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']} [04:51] [ComfyUI] Found comfy_kitchen backend cuda: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']} [04:51] [ComfyUI] 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']} [04:51] [ComfyUI] Checkpoint files will always be loaded safely. [04:52] [ComfyUI] Total VRAM 24124 MB, total RAM 31924 MB [04:52] [ComfyUI] pytorch version: 2.11.0+cu128 [04:52] [ComfyUI] Set vram state to: NORMAL_VRAM [04:52] [ComfyUI] Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync [04:52] [ComfyUI] Using async weight offloading with 2 streams [04:52] [ComfyUI] Enabled pinned memory 28731.0 [04:52] [ComfyUI] Using pytorch attention [04:58] [ComfyUI] aimdo: /project/src-posix/cuda-funchooks.c:52:DEBUG:aimdo_setup_hooks: hooks successfully installed [04:58] [ComfyUI] aimdo: /project/src/control.c:151:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 3090 (VRAM: 24124 MB) [04:58] [ComfyUI] DynamicVRAM support detected and enabled [04:58] [ComfyUI] Python version: 3.12.13 (main, May 8 2026, 18:32:55) [Clang 22.1.3 ] [04:58] [ComfyUI] ComfyUI version: 0.20.1 [04:58] [ComfyUI] comfy-aimdo version: 0.3.0 [04:58] [ComfyUI] comfy-kitchen version: 0.2.8 [04:58] [ComfyUI] ****** User settings have been changed to be stored on the server instead of browser storage. ****** [04:58] [ComfyUI] ****** For multi-user setups add the --multi-user CLI argument to enable multiple user profiles. ****** [04:58] [ComfyUI] ComfyUI frontend version: 1.43.18 [04:58] [ComfyUI] [Prompt Server] web root: /workspaces/DepthAnythingV3-1418/.venv/lib/python3.12/site-packages/comfyui_frontend_package/static [04:58] [ComfyUI] Asset seeder disabled [05:00] [ComfyUI] [comfy-env] Version: 0.3.78 [05:00] [ComfyUI] [comfy-env] register_nodes: ComfyUI-DepthAnythingV3 [05:00] [ComfyUI] [comfy-env] ComfyUI source dir: /workspaces/DepthAnythingV3-1418/ComfyUI [05:01] [ComfyUI] [comfy-env] Found 1 isolation env(s) [05:01] [ComfyUI] [comfy-env] Scanning nodes metadata (isolation root)... [05:01] [ComfyUI] [comfy-env] Metadata scan: /root/.pixi/bin/pixi run --as-is --manifest-path /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml -e depthanythingv3-nodes python /tmp/comfy_meta_r3_beyd9.py /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 nodes [05:01] [ComfyUI] [comfy-env] Scan env PATH for nodes: [05:01] [ComfyUI] [comfy-env] [0] /root/.local/bin [05:01] [ComfyUI] [comfy-env] [1] /usr/local/nvidia/bin [05:01] [ComfyUI] [comfy-env] [2] /usr/local/cuda/bin [05:01] [ComfyUI] [comfy-env] [3] /usr/local/sbin [05:01] [ComfyUI] [comfy-env] [4] /usr/local/bin [05:01] [ComfyUI] [comfy-env] [5] /usr/sbin [05:01] [ComfyUI] [comfy-env] [6] /usr/bin [05:01] [ComfyUI] [comfy-env] [7] /sbin [05:01] [ComfyUI] [comfy-env] [8] /bin [05:08] [ComfyUI] [comfy-env] Metadata scan stderr for nodes: [05:08] [ComfyUI] [comfy-env] [meta-scan] importing nodes from /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 [05:08] [ComfyUI] [comfy-env] WARNING:root:WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [05:08] [ComfyUI] [comfy-env] [meta-scan] import OK [05:08] [ComfyUI] [comfy-env] Scanned nodes: 15 nodes (7.7s) [05:08] [ComfyUI] [comfy-env] Scanned nodes root: 15 nodes (7.7s) [05:08] [ComfyUI] [comfy-env] Imported nodes root: 15 nodes (isolation) [05:08] [ComfyUI] [comfy-env] Registered 15 total nodes [05:08] [ComfyUI] loading... [05:08] [ComfyUI] calling register_nodes [05:08] [ComfyUI] [comfy-env] Version: 0.3.78 [05:08] [ComfyUI] [comfy-env] register_nodes: ComfyUI-GeometryPack [05:08] [ComfyUI] [comfy-env] ComfyUI source dir: /workspaces/DepthAnythingV3-1418/ComfyUI [05:08] [ComfyUI] [comfy-env] Found 1 isolation env(s) [05:08] [ComfyUI] [comfy-env] Scanning nodes metadata (isolation root)... [05:08] [ComfyUI] [comfy-env] Metadata scan: /root/.pixi/bin/pixi run --as-is --manifest-path /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml -e geometrypack-nodes python /tmp/comfy_meta_pa2jfp2b.py /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-GeometryPack nodes [05:08] [ComfyUI] [comfy-env] Scan env PATH for nodes: [05:08] [ComfyUI] [comfy-env] [0] /root/.local/bin [05:08] [ComfyUI] [comfy-env] [1] /usr/local/nvidia/bin [05:08] [ComfyUI] [comfy-env] [2] /usr/local/cuda/bin [05:08] [ComfyUI] [comfy-env] [3] /usr/local/sbin [05:08] [ComfyUI] [comfy-env] [4] /usr/local/bin [05:08] [ComfyUI] [comfy-env] [5] /usr/sbin [05:08] [ComfyUI] [comfy-env] [6] /usr/bin [05:08] [ComfyUI] [comfy-env] [7] /sbin [05:08] [ComfyUI] [comfy-env] [8] /bin [05:19] [ComfyUI] [comfy-env] Metadata scan stderr for nodes: [05:19] [ComfyUI] [comfy-env] [meta-scan] importing nodes from /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-GeometryPack [05:19] [ComfyUI] [comfy-env] WARNING:root:WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [05:19] [ComfyUI] [comfy-env] [meta-scan] import OK [05:19] [ComfyUI] [comfy-env] Scanned nodes: 125 nodes (11.0s) [05:19] [ComfyUI] [comfy-env] Scanned nodes root: 125 nodes (11.0s) [05:19] [ComfyUI] [comfy-env] Imported nodes root: 125 nodes (isolation) [05:19] [ComfyUI] [comfy-env] Registered 125 total nodes [05:20] [ComfyUI] [05:20] [ComfyUI] Import times for custom nodes: [05:20] [ComfyUI] 0.0 seconds: /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-validate-endpoint [05:20] [ComfyUI] 0.0 seconds: /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/websocket_image_save.py [05:20] [ComfyUI] 0.1 seconds: /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite [05:20] [ComfyUI] 0.2 seconds: /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-KJNodes [05:20] [ComfyUI] 7.9 seconds: /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 [05:20] [ComfyUI] 11.1 seconds: /workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-GeometryPack [05:20] [ComfyUI] [05:20] [ComfyUI] Context impl SQLiteImpl. [05:20] [ComfyUI] Will assume non-transactional DDL. [05:20] [ComfyUI] Context impl SQLiteImpl. [05:20] [ComfyUI] Will assume non-transactional DDL. [05:20] [ComfyUI] Running upgrade -> 0001_assets, Initial assets schema [05:20] [ComfyUI] Revision ID: 0001_assets [05:20] [ComfyUI] Revises: None [05:20] [ComfyUI] Create Date: 2025-12-10 00:00:00 [05:20] [ComfyUI] Running upgrade 0001_assets -> 0002_merge_to_asset_references, Merge AssetInfo and AssetCacheState into unified asset_references table. [05:20] [ComfyUI] Running upgrade 0002_merge_to_asset_references -> 0003_add_metadata_job_id, Add system_metadata and job_id columns to asset_references. [05:20] [ComfyUI] Change preview_id FK from assets.id to asset_references.id. [05:20] [ComfyUI] Database upgraded from None to 0003_add_metadata_job_id [05:20] [ComfyUI] Starting server [05:20] [ComfyUI] [05:20] [ComfyUI] To see the GUI go to: http://127.0.0.1:41890 [05:21] Server responding, waiting for nodes to load... [05:41] Server is ready! [05:41] Checking for import errors in server logs... [05:41] No import errors detected [05:41] Found 1120 registered nodes [05:41] [REGISTRATION] PASSED [05:41] [05:41] [4/5] INSTANTIATION [05:41] ---------------------------------------- [05:41] [DEBUG] server=, server_url=None, api= [05:41] Testing node constructors... [05:42] All 15 node(s) instantiated successfully! [05:42] [INSTANTIATION] PASSED [05:42] [05:42] [5/5] EXECUTION [05:42] ---------------------------------------- [05:42] [DEBUG] server=, server_url=None, api= [05:42] GPU runner - will execute 7 workflow(s) [05:42] Running 7 workflow(s) (all with videos)... [05:42] Installing screenshot dependencies (playwright, pillow)... [05:43] Packages installed, downloading chromium browser... [06:06] Screenshot dependencies installed successfully [06:06] Starting headless browser... [06:07] Installing Vulkan stack (apt)... [06:07] Vulkan install error: [Errno 2] No such file or directory: 'sudo' [06:07] GPU detected (no Vulkan) -- using ANGLE/OpenGL rendering [06:07] Capturing execution frames: advanced.json [06:09] [ComfyUI] [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. [06:15] Frame 1 saved (frame_000.jpg, t=0.0s) [06:15] Validating workflow... [06:15] [ComfyUI] === /validate endpoint called === [06:15] [ComfyUI] Received JSON with keys: ['prompt'] [06:15] [ComfyUI] Prompt has 11 nodes [06:15] Queuing workflow for execution... [06:15] [ComfyUI] Node 2: LoadImage [06:15] [ComfyUI] Inputs: {"image": "bridge.jpg"} [06:15] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [06:15] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [06:15] [ComfyUI] Node 4: PreviewImage [06:15] [ComfyUI] Inputs: {"images": ["12", 0]} [06:15] [ComfyUI] Node 6: PreviewImage [06:15] [ComfyUI] Inputs: {"images": ["12", 1]} [06:15] [ComfyUI] Node 7: PreviewImage [06:15] [ComfyUI] Inputs: {"images": ["12", 2]} [06:15] [ComfyUI] Node 8: PreviewImage [06:15] [ComfyUI] Inputs: {"images": ["12", 3]} [06:15] [ComfyUI] Node 9: PreviewAny [06:15] [ComfyUI] Inputs: {"source": ["12", 6]} [06:15] [ComfyUI] Node 10: PreviewAny [06:15] [ComfyUI] Inputs: {"source": ["12", 5]} [06:15] [ComfyUI] Node 11: MaskPreview [06:15] [ComfyUI] Inputs: {"mask": ["12", 7]} [06:15] [ComfyUI] Node 12: DepthAnything_V3 [06:15] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} [06:15] [ComfyUI] [comfy-env] SubprocessWorker: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:15] [ComfyUI] Node 13: PreviewImage [06:15] [ComfyUI] [comfy-env] env_vars: {'COMFYUI_BASE': '/workspaces/DepthAnythingV3-1418/ComfyUI'} [06:15] [ComfyUI] Inputs: {"images": ["12", 4]} [06:15] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:15] [ComfyUI] Generated prompt_id: 14aeaa06-4a19-43f1-98bb-e9412fa8941b [06:15] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1418/ComfyUI', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [06:15] [ComfyUI] Calling execution.validate_prompt()... [06:15] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:15] [ComfyUI] Validation result: valid=True [06:15] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py', 'abstract://comfy_worker_c855d870e68a']... [06:15] [ComfyUI] === Validation PASSED === [06:15] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_c855d870e68a (abstract, no filesystem path) [06:15] [ComfyUI] got prompt [06:15] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [06:15] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 302 / 24124 MB [06:15] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [06:15] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [06:18] Frame 2 saved (frame_001.jpg, t=2.5s) [06:18] [capture-periodic] freeze=4ms shot=196ms unfreeze=4ms saved=True [06:18] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [06:18] [ComfyUI] [SubprocessWorker] worker started/confirmed [06:18] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [06:18] [ComfyUI] [SubprocessWorker] created 0 shm blocks [06:18] [ComfyUI] [SubprocessWorker] sending request via socket... [06:18] [ComfyUI] [SubprocessWorker] call_id=1 sending call_method [06:19] [ComfyUI] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. [06:19] [ComfyUI] [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. [06:20] [ComfyUI] [06:20] Frame 3 saved (frame_002.jpg, t=4.8s) [06:20] [capture-periodic] freeze=3ms shot=191ms unfreeze=3ms saved=True [06:21] [capture-loop] iter=50 t=6.3s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=4.2/31.2GB (13%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.86GB [06:24] [ComfyUI] model.safetensors: 0%| | 0.00/1.64G [00:00 cpu: 3239 / 24124 MB [06:45] Capturing execution frames: advanced_3d.json [06:45] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [06:45] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [06:45] [ComfyUI] [SubprocessWorker] call_id=3 sending model_to_device [06:45] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -229MB (now 743MB) reserved=2592MB peak=1581MB [06:46] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 711 / 24124 MB [06:52] Frame 1 saved (frame_000.jpg, t=0.0s) [06:52] Validating workflow... [06:52] [ComfyUI] === /validate endpoint called === [06:52] [ComfyUI] Received JSON with keys: ['prompt'] [06:52] [ComfyUI] Prompt has 6 nodes [06:52] Queuing workflow for execution... [06:52] [ComfyUI] Node 2: LoadImage [06:52] [ComfyUI] Inputs: {"image": "kaffi.jpg"} [06:52] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [06:52] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [06:52] [ComfyUI] Node 21: DepthAnything_V3 [06:52] [ComfyUI] Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} [06:52] [ComfyUI] Node 22: DA3_ToPointCloud [06:52] [ComfyUI] 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 [06:52] [ComfyUI] Node 23: DA3_SavePointCloud [06:52] [ComfyUI] Inputs: {"filename_prefix": "pointcloud", "pointcloud": ["22", 0]} [06:52] [ComfyUI] Node 25: DA3_PreviewPointCloud [06:52] [ComfyUI] Inputs: {"file_path": ["23", 0], "color_mode": "RGB", "preview_vtk": ""} [06:52] [ComfyUI] Generated prompt_id: 4ca083cb-84e0-42c1-b007-b3f345a772d8 [06:52] [ComfyUI] Calling execution.validate_prompt()... [06:52] [ComfyUI] Validation result: valid=True [06:52] [ComfyUI] === Validation PASSED === [06:52] [ComfyUI] got prompt [06:52] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [06:52] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 711 / 24124 MB [06:52] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [06:52] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:52] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [06:52] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1418/ComfyUI', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [06:52] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [06:52] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:52] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [06:52] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py', 'abstract://comfy_worker_0e2e1d830f73']... [06:52] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [06:52] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_0e2e1d830f73 (abstract, no filesystem path) [06:52] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [06:55] Frame 2 saved (frame_001.jpg, t=2.5s) [06:55] [capture-periodic] freeze=3ms shot=203ms unfreeze=7ms saved=True [06:55] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [06:55] [ComfyUI] [SubprocessWorker] worker started/confirmed [06:55] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [06:55] [ComfyUI] [SubprocessWorker] created 0 shm blocks [06:55] [ComfyUI] [SubprocessWorker] sending request via socket... [06:55] [ComfyUI] [SubprocessWorker] call_id=4 sending call_method [06:56] [ComfyUI] [SubprocessWorker] got response: ok [06:56] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 563 / 24124 MB [06:56] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [06:56] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [06:56] [ComfyUI] [SubprocessWorker] call_id=5 sending model_to_device [06:56] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [06:56] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 563 / 24124 MB [06:56] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (3.49s): result: NodeOutput [06:56] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 563 / 24124 MB [06:56] [ComfyUI] [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 [06:56] [ComfyUI] [VRAM] Before DepthAnything_V3: 563 / 24124 MB [06:56] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [06:56] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [06:56] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [06:56] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [06:56] [ComfyUI] [SubprocessWorker] worker started/confirmed [06:56] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 533, 800, 3]) [06:56] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [06:56] [ComfyUI] [SubprocessWorker] created 0 shm blocks [06:56] [ComfyUI] [SubprocessWorker] sending request via socket... [06:56] [ComfyUI] [SubprocessWorker] call_id=6 sending call_method [06:56] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [06:56] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 533, 800, 3] [06:56] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 533, 800, 3]) [06:57] Frame 3 saved (frame_002.jpg, t=4.8s) [06:57] [capture-periodic] freeze=3ms shot=177ms unfreeze=7ms saved=True [06:57] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=6 [06:57] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 24.71GB [06:57] [ComfyUI] [comfy-env] VRAM after eviction: 24.71GB [06:57] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +650MB (now 650MB) reserved=672MB peak=650MB [06:58] [capture-loop] iter=50 t=6.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=4.7/31.2GB (15%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.95GB [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +212MB (now 863MB) reserved=928MB peak=863MB [06:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=6 [06:59] [ComfyUI] [SubprocessWorker] got response: ok [06:59] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [06:59] [ComfyUI] [comfy-env] DepthAnything_V3 done (3.67s): result: NodeOutput [06:59] [ComfyUI] [VRAM] After DepthAnything_V3: 2567 / 24124 MB [06:59] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [06:59] [ComfyUI] [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 [06:59] [ComfyUI] [VRAM] Before DA3_ToPointCloud: 2567 / 24124 MB [06:59] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [06:59] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_ToPointCloud.EXECUTE_NORMALIZED [06:59] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [06:59] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [06:59] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [06:59] [ComfyUI] [SubprocessWorker] worker started/confirmed [06:59] [ComfyUI] [comfy-env] PRE-SERIALIZE 'depth_raw' shape: torch.Size([1, 532, 800, 3]) [06:59] [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 532, 800, 3]) [06:59] [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 532, 800]) [06:59] [ComfyUI] [comfy-env] PRE-SERIALIZE 'source_image' shape: torch.Size([1, 532, 800, 3]) [06:59] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [06:59] [ComfyUI] [SubprocessWorker] created 0 shm blocks [06:59] [ComfyUI] [SubprocessWorker] sending request via socket... [06:59] [ComfyUI] [SubprocessWorker] call_id=7 sending call_method [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800] [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800]) [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [06:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [07:00] [ComfyUI] [SubprocessWorker] got response: ok [07:00] [ComfyUI] [comfy-env] DA3_ToPointCloud done (0.25s): result: NodeOutput [07:00] [ComfyUI] [VRAM] After DA3_ToPointCloud: 2567 / 24124 MB [07:00] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:00] [ComfyUI] [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [07:00] [ComfyUI] [VRAM] Before DA3_SavePointCloud: 2567 / 24124 MB [07:00] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:00] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [07:00] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:00] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:00] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:00] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:00] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:00] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:00] [ComfyUI] [SubprocessWorker] sending request via socket... [07:00] [ComfyUI] [SubprocessWorker] call_id=8 sending call_method [07:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[310685, 3] [07:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([310685, 3]) [07:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[310685] [07:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([310685]) [07:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[310685, 3] [07:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([310685, 3]) [07:01] Frame 4 saved (frame_003.jpg, t=9.3s) [07:01] [capture-periodic] freeze=3ms shot=209ms unfreeze=3ms saved=True [07:03] [ComfyUI] [SubprocessWorker] got response: ok [07:03] [ComfyUI] [comfy-env] DA3_SavePointCloud done (3.09s): result: NodeOutput [07:03] [ComfyUI] [VRAM] After DA3_SavePointCloud: 2567 / 24124 MB [07:03] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:03] [ComfyUI] [comfy-env] Running DA3_PreviewPointCloud: file_path: '/workspaces/DepthAnythingV3-1418/ComfyUI/output/pointclo..., color_mode: 'RGB' [07:03] [ComfyUI] [VRAM] Before DA3_PreviewPointCloud: 2567 / 24124 MB [07:03] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:03] [ComfyUI] [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [07:03] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:03] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:03] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:03] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:03] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:03] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:03] [ComfyUI] [SubprocessWorker] sending request via socket... [07:03] [ComfyUI] [SubprocessWorker] call_id=9 sending call_method [07:03] [ComfyUI] [SubprocessWorker] got response: ok [07:03] [ComfyUI] [comfy-env] DA3_PreviewPointCloud done (0.06s): result: NodeOutput [07:03] [ComfyUI] [VRAM] After DA3_PreviewPointCloud: 2567 / 24124 MB [07:03] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:03] [ComfyUI] Prompt executed in 10.62 seconds [07:03] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 2567 / 24124 MB [07:03] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:03] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:03] [ComfyUI] [SubprocessWorker] call_id=10 sending model_to_device [07:03] Node executed (2 total), capturing... [07:03] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -296MB (now 567MB) reserved=1920MB peak=1214MB [07:03] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 711 / 24124 MB [07:05] Frame 5 saved (frame_004.jpg, t=11.1s) [07:05] [capture-node] freeze=1514ms shot=178ms unfreeze=0ms saved=True [07:05] Execution complete (t=11.1s) [07:05] Captured 5 unique frames over 12.91s [07:05] [debug] iframes: 1 [07:05] [debug] iframe[0]: src=http://127.0.0.1:41890/extensions/ComfyUI-GeometryPack/viewer_vtk.html?v=1778423, canvas=486x394, rafFrozen=True [07:05] [timing] trigger_3d_previews: 0.0s [07:07] Saved high-quality screenshot: advanced_3d_executed.png [07:07] [timing] final_screenshot: 0.5s [07:07] Capturing execution frames: advanced_3d_multiview.json [07:15] Frame 1 saved (frame_000.jpg, t=0.0s) [07:15] Validating workflow... [07:15] [ComfyUI] === /validate endpoint called === [07:15] [ComfyUI] Received JSON with keys: ['prompt'] [07:15] [ComfyUI] Prompt has 8 nodes [07:15] Queuing workflow for execution... [07:15] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [07:15] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [07:15] [ComfyUI] Node 21: LoadImageDataSetFromFolder [07:15] [ComfyUI] Inputs: {"folder": "SOH"} [07:15] [ComfyUI] Node 27: PreviewImage [07:15] [ComfyUI] Inputs: {"images": ["21", 0]} [07:15] [ComfyUI] Node 38: DA3_MultiViewPointCloud [07:15] [ComfyUI] 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": [07:15] [ComfyUI] Node 39: DepthAnythingV3_MultiView [07:15] [ComfyUI] Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["21", 0]} [07:15] [ComfyUI] Node 44: DA3_SavePointCloud [07:15] [ComfyUI] Inputs: {"filename_prefix": "pointcloud", "pointcloud": ["38", 0]} [07:15] [ComfyUI] Node 45: PreviewAny [07:15] [ComfyUI] Inputs: {"source": ["44", 0]} [07:15] [ComfyUI] Node 48: DA3_PreviewPointCloud [07:15] [ComfyUI] Inputs: {"file_path": ["44", 0], "color_mode": "RGB", "preview_vtk": ""} [07:15] [ComfyUI] Generated prompt_id: cd6f02a0-0a58-4016-bd5e-8e5f6b67dcb6 [07:15] [ComfyUI] Calling execution.validate_prompt()... [07:15] [ComfyUI] Validation result: valid=True [07:15] [ComfyUI] === Validation PASSED === [07:15] [ComfyUI] got prompt [07:15] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [07:15] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 711 / 24124 MB [07:15] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [07:15] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [07:15] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1418/ComfyUI', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [07:15] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:15] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [07:15] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:15] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py', 'abstract://comfy_worker_78048eaa4483']... [07:15] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [07:15] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_78048eaa4483 (abstract, no filesystem path) [07:15] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [07:15] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [07:15] Node executed (1 total), capturing... [07:16] Frame 2 saved (frame_001.jpg, t=0.9s) [07:16] [capture-node] freeze=5ms shot=208ms unfreeze=4ms saved=True [07:18] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [07:18] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:18] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:18] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:18] [ComfyUI] [SubprocessWorker] sending request via socket... [07:18] [ComfyUI] [SubprocessWorker] call_id=11 sending call_method [07:19] [ComfyUI] [SubprocessWorker] got response: ok [07:19] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 563 / 24124 MB [07:19] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:19] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:19] [ComfyUI] [SubprocessWorker] call_id=12 sending model_to_device [07:19] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [07:19] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 563 / 24124 MB [07:19] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (3.50s): result: NodeOutput [07:19] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 563 / 24124 MB [07:19] [ComfyUI] [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 [07:19] [ComfyUI] [VRAM] Before DepthAnythingV3_MultiView: 563 / 24124 MB [07:19] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [07:19] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:19] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:19] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:19] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:19] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [07:19] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:19] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:19] [ComfyUI] [SubprocessWorker] sending request via socket... [07:19] [ComfyUI] [SubprocessWorker] call_id=13 sending call_method [07:19] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:19] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [07:19] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [07:20] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=13 [07:20] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 24.71GB [07:20] [ComfyUI] [comfy-env] VRAM after eviction: 24.71GB [07:20] Frame 3 saved (frame_002.jpg, t=5.4s) [07:20] [capture-periodic] freeze=3ms shot=189ms unfreeze=8ms saved=True [07:20] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +626MB (now 626MB) reserved=640MB peak=626MB [07:21] [capture-loop] iter=50 t=6.7s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=4.9/31.2GB (16%) swap=0.0/32.0GB (0%) cpu=6% browser_rss=0.99GB [07:21] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +237MB (now 863MB) reserved=896MB peak=863MB [07:23] [ComfyUI] [SubprocessWorker] got response: ok [07:23] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [07:23] [ComfyUI] [comfy-env] DepthAnythingV3_MultiView done (3.89s): result: NodeOutput [07:23] [ComfyUI] [VRAM] After DepthAnythingV3_MultiView: 4007 / 24124 MB [07:23] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:23] [ComfyUI] [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 [07:23] [ComfyUI] [VRAM] Before DepthAnythingV3_MultiView: 4007 / 24124 MB [07:23] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:23] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [07:23] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:23] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:23] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:23] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:23] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [07:23] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:23] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:23] [ComfyUI] [SubprocessWorker] sending request via socket... [07:23] [ComfyUI] [SubprocessWorker] call_id=14 sending call_method [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [07:23] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=14 [07:23] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 21.09GB [07:23] [ComfyUI] [comfy-env] VRAM after eviction: 21.09GB [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +376MB (now 1240MB) reserved=1472MB peak=1628MB [07:23] [ComfyUI] [SubprocessWorker] got response: ok [07:23] [ComfyUI] [comfy-env] DepthAnythingV3_MultiView done (0.69s): result: NodeOutput [07:23] [ComfyUI] [VRAM] After DepthAnythingV3_MultiView: 3527 / 24124 MB [07:23] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:23] [ComfyUI] [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 [07:23] [ComfyUI] [VRAM] Before DA3_MultiViewPointCloud: 3527 / 24124 MB [07:23] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:23] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DA3_MultiViewPointCloud.EXECUTE_NORMALIZED [07:23] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:23] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:23] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:23] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:23] [ComfyUI] [comfy-env] PRE-SERIALIZE 'depths' shape: torch.Size([1, 680, 1208, 3]) [07:23] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [07:23] [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 680, 1208, 3]) [07:23] [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 680, 1208]) [07:23] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:23] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:23] [ComfyUI] [SubprocessWorker] sending request via socket... [07:23] [ComfyUI] [SubprocessWorker] call_id=15 sending call_method [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208] [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208]) [07:24] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=15 [07:24] [ComfyUI] [SubprocessWorker] got response: ok [07:24] [ComfyUI] [comfy-env] DA3_MultiViewPointCloud done (0.25s): result: NodeOutput [07:24] [ComfyUI] [VRAM] After DA3_MultiViewPointCloud: 3527 / 24124 MB [07:24] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:24] [ComfyUI] [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 [07:24] [ComfyUI] [VRAM] Before DA3_MultiViewPointCloud: 3527 / 24124 MB [07:24] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:24] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DA3_MultiViewPointCloud.EXECUTE_NORMALIZED [07:24] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:24] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:24] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:24] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:24] [ComfyUI] [comfy-env] PRE-SERIALIZE 'depths' shape: torch.Size([1, 680, 1208, 3]) [07:24] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [07:24] [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 680, 1208, 3]) [07:24] [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 680, 1208]) [07:24] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:24] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:24] [ComfyUI] [SubprocessWorker] sending request via socket... [07:24] [ComfyUI] [SubprocessWorker] call_id=16 sending call_method [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208]) [07:24] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=16 [07:24] [ComfyUI] [SubprocessWorker] got response: ok [07:24] [ComfyUI] [comfy-env] DA3_MultiViewPointCloud done (0.25s): result: NodeOutput [07:24] [ComfyUI] [VRAM] After DA3_MultiViewPointCloud: 3527 / 24124 MB [07:24] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:24] [ComfyUI] [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [07:24] [ComfyUI] [VRAM] Before DA3_SavePointCloud: 3527 / 24124 MB [07:24] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:24] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [07:24] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:24] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:24] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:24] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:24] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:24] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:24] [ComfyUI] [SubprocessWorker] sending request via socket... [07:24] [ComfyUI] [SubprocessWorker] call_id=17 sending call_method [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18824, 3] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18824, 3]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18824, 3] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18824, 3]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18824] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18824]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18824] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18824]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -448MB (now 793MB) reserved=2880MB peak=1628MB [07:24] [ComfyUI] [SubprocessWorker] got response: ok [07:24] [ComfyUI] [comfy-env] DA3_SavePointCloud done (0.46s): result: NodeOutput [07:24] [ComfyUI] [VRAM] After DA3_SavePointCloud: 3527 / 24124 MB [07:24] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:24] [ComfyUI] [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [07:24] [ComfyUI] [VRAM] Before DA3_SavePointCloud: 3527 / 24124 MB [07:24] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:24] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [07:24] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:24] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:24] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:24] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:24] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:24] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:24] [ComfyUI] [SubprocessWorker] sending request via socket... [07:24] [ComfyUI] [SubprocessWorker] call_id=18 sending call_method [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20457, 3] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20457, 3]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20457, 3] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20457, 3]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20457] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20457]) [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20457] [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20457]) [07:25] [ComfyUI] [SubprocessWorker] got response: ok [07:25] [ComfyUI] [comfy-env] DA3_SavePointCloud done (0.47s): result: NodeOutput [07:25] [ComfyUI] [VRAM] After DA3_SavePointCloud: 3527 / 24124 MB [07:25] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:25] [ComfyUI] [comfy-env] Running DA3_PreviewPointCloud: file_path: '/workspaces/DepthAnythingV3-1418/ComfyUI/output/pointclo..., color_mode: 'RGB' [07:25] [ComfyUI] [VRAM] Before DA3_PreviewPointCloud: 3527 / 24124 MB [07:25] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:25] [ComfyUI] [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [07:25] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:25] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:25] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:25] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:25] [ComfyUI] [SubprocessWorker] sending request via socket... [07:25] [ComfyUI] [SubprocessWorker] call_id=19 sending call_method [07:25] [ComfyUI] [SubprocessWorker] got response: ok [07:25] [ComfyUI] [comfy-env] DA3_PreviewPointCloud done (0.06s): result: NodeOutput [07:25] [ComfyUI] [VRAM] After DA3_PreviewPointCloud: 3527 / 24124 MB [07:25] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:25] [ComfyUI] [comfy-env] Running DA3_PreviewPointCloud: file_path: '/workspaces/DepthAnythingV3-1418/ComfyUI/output/pointclo..., color_mode: 'RGB' [07:25] [ComfyUI] [VRAM] Before DA3_PreviewPointCloud: 3527 / 24124 MB [07:25] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:25] [ComfyUI] [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [07:25] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:25] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:25] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:25] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:25] [ComfyUI] [SubprocessWorker] sending request via socket... [07:25] [ComfyUI] [SubprocessWorker] call_id=20 sending call_method [07:25] [ComfyUI] [SubprocessWorker] got response: ok [07:25] [ComfyUI] [comfy-env] DA3_PreviewPointCloud done (0.07s): result: NodeOutput [07:25] [ComfyUI] [VRAM] After DA3_PreviewPointCloud: 3527 / 24124 MB [07:25] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:25] [ComfyUI] Prompt executed in 9.97 seconds [07:25] Frame 4 saved (frame_003.jpg, t=10.0s) [07:25] [capture-periodic] freeze=3ms shot=208ms unfreeze=5ms saved=True [07:25] Node executed (4 total), capturing... [07:26] Frame 5 saved (frame_004.jpg, t=10.6s) [07:26] [capture-node] freeze=4ms shot=307ms unfreeze=22ms saved=True [07:26] Execution complete (t=11.1s) [07:26] Captured 5 unique frames over 11.14s [07:26] [debug] iframes: 1 [07:26] [debug] iframe[0]: src=http://127.0.0.1:41890/extensions/ComfyUI-DepthAnythingV3/viewer_vtk.html?v=1778, canvas=486x394, rafFrozen=False [07:26] [timing] trigger_3d_previews: 0.0s [07:28] Saved high-quality screenshot: advanced_3d_multiview_executed.png [07:28] [timing] final_screenshot: 0.5s [07:28] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 3527 / 24124 MB [07:28] Capturing execution frames: bas_relief.json [07:28] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:28] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:28] [ComfyUI] [SubprocessWorker] call_id=21 sending model_to_device [07:28] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -242MB (now 551MB) reserved=2880MB peak=1628MB [07:29] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 711 / 24124 MB [07:36] Frame 1 saved (frame_000.jpg, t=0.0s) [07:36] Validating workflow... [07:36] [ComfyUI] === /validate endpoint called === [07:36] [ComfyUI] Received JSON with keys: ['prompt'] [07:36] [ComfyUI] Prompt has 6 nodes [07:36] Queuing workflow for execution... [07:36] [ComfyUI] Node 2: LoadImage [07:36] [ComfyUI] Inputs: {"image": "bas_relief.png"} [07:36] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [07:36] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [07:36] [ComfyUI] Node 21: DepthAnything_V3 [07:36] [ComfyUI] Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": true, "da3_model": ["3", 0], "images": ["2", 0]} [07:36] [ComfyUI] Node 27: PreviewImage [07:36] [ComfyUI] Inputs: {"images": ["21", 2]} [07:36] [ComfyUI] Node 30: Preview3D [07:36] [ComfyUI] Inputs: {"model_file": ["32", 0], "image": ""} [07:36] [ComfyUI] Node 32: DA3_ToMesh [07:36] [ComfyUI] 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 [07:36] [ComfyUI] Generated prompt_id: 577469fe-a114-40ea-9760-9e511268b5de [07:36] [ComfyUI] Calling execution.validate_prompt()... [07:36] [ComfyUI] Validation result: valid=True [07:36] [ComfyUI] === Validation PASSED === [07:36] [ComfyUI] got prompt [07:36] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [07:36] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 711 / 24124 MB [07:36] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [07:36] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [07:36] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1418/ComfyUI', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [07:36] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:36] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [07:36] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:36] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py', 'abstract://comfy_worker_72db68db4867']... [07:36] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [07:36] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_72db68db4867 (abstract, no filesystem path) [07:36] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [07:36] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [07:39] Frame 2 saved (frame_001.jpg, t=2.5s) [07:39] [capture-periodic] freeze=3ms shot=228ms unfreeze=4ms saved=True [07:39] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [07:40] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:40] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:40] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:40] [ComfyUI] [SubprocessWorker] sending request via socket... [07:40] [ComfyUI] [SubprocessWorker] call_id=22 sending call_method [07:40] [ComfyUI] [SubprocessWorker] got response: ok [07:40] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 563 / 24124 MB [07:40] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:40] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:40] [ComfyUI] [SubprocessWorker] call_id=23 sending model_to_device [07:40] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [07:40] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 563 / 24124 MB [07:40] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (3.36s): result: NodeOutput [07:40] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 563 / 24124 MB [07:40] [ComfyUI] [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 [07:40] [ComfyUI] [VRAM] Before DepthAnything_V3: 563 / 24124 MB [07:40] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [07:40] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:40] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:40] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:40] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:40] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 2000, 1336, 3]) [07:40] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:40] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:40] [ComfyUI] [SubprocessWorker] sending request via socket... [07:40] [ComfyUI] [SubprocessWorker] call_id=24 sending call_method [07:40] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:40] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2000, 1336, 3] [07:40] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2000, 1336, 3]) [07:41] Frame 3 saved (frame_002.jpg, t=4.8s) [07:41] [capture-periodic] freeze=3ms shot=239ms unfreeze=7ms saved=True [07:41] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=24 [07:41] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 24.71GB [07:41] [ComfyUI] [comfy-env] VRAM after eviction: 24.71GB [07:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +210MB (now 210MB) reserved=224MB peak=210MB [07:42] [capture-loop] iter=50 t=6.4s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=5.2/31.2GB (16%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=1.01GB [07:42] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +810MB (now 1021MB) reserved=1056MB peak=1021MB [07:43] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +882MB (now 1903MB) reserved=2336MB peak=1903MB [07:44] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=24 [07:44] [ComfyUI] [SubprocessWorker] got response: ok [07:44] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [07:44] [ComfyUI] [comfy-env] DepthAnything_V3 done (4.44s): result: NodeOutput [07:44] [ComfyUI] [VRAM] After DepthAnything_V3: 7655 / 24124 MB [07:44] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:44] [ComfyUI] [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 [07:44] [ComfyUI] [VRAM] Before DA3_ToMesh: 7655 / 24124 MB [07:44] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:44] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_ToMesh.EXECUTE_NORMALIZED [07:44] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:44] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:44] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:44] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:44] [ComfyUI] [comfy-env] PRE-SERIALIZE 'depth_raw' shape: torch.Size([1, 2002, 1330, 3]) [07:44] [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 2002, 1330, 3]) [07:44] [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 2002, 1330]) [07:44] [ComfyUI] [comfy-env] PRE-SERIALIZE 'source_image' shape: torch.Size([1, 2002, 1330, 3]) [07:44] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:44] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:44] [ComfyUI] [SubprocessWorker] sending request via socket... [07:44] [ComfyUI] [SubprocessWorker] call_id=25 sending call_method [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330, 3] [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330, 3]) [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330, 3] [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330, 3]) [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330] [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330]) [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330, 3] [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -1111MB (now 793MB) reserved=7008MB peak=3681MB [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330, 3]) [07:45] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: pyfqmr not installed, skipping decimation. Install with: pip install pyfqmr [07:46] Frame 4 saved (frame_003.jpg, t=9.5s) [07:46] [capture-periodic] freeze=3ms shot=228ms unfreeze=11ms saved=True [07:48] [capture-loop] iter=100 t=12.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=6.3/31.2GB (20%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=1.01GB [07:48] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: pygltflib is required for material post-processing. Install with: pip install pygltflib. Mesh may appear dark or single-sided. [07:48] [ComfyUI] [SubprocessWorker] got response: ok [07:48] [ComfyUI] [comfy-env] DA3_ToMesh done (4.24s): result: NodeOutput [07:48] [ComfyUI] [VRAM] After DA3_ToMesh: 7691 / 24124 MB [07:48] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [07:49] Node executed (2 total), capturing... [07:49] [ComfyUI] Prompt executed in 12.76 seconds [07:49] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 7691 / 24124 MB [07:49] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:49] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:49] [ComfyUI] [SubprocessWorker] call_id=26 sending model_to_device [07:49] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -248MB (now 545MB) reserved=7008MB peak=3681MB [07:50] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 747 / 24124 MB [07:54] Frame 5 saved (frame_004.jpg, t=13.2s) [07:54] [capture-node] freeze=297ms shot=4209ms unfreeze=28ms saved=True [07:54] Node executed (3 total), capturing... [08:00] Frame 6 saved (frame_005.jpg, t=18.2s) [08:00] [capture-node] freeze=57ms shot=6071ms unfreeze=0ms saved=True [08:00] Execution complete (t=18.2s) [08:00] [3d-wait] Phase 1: Waiting for 'Loading 3D Model' text to disappear... [09:00] [3d-wait] Phase 1 exception after 60.0s: Page.wait_for_function: Timeout 60000ms exceeded. [09:00] [3d-wait] Phase 2: iframes=0 [09:00] [3d-wait] Total 3D wait: 60.0s [09:00] Captured 6 unique frames over 84.44s [09:00] [debug] iframes: 0 [09:00] [timing] trigger_3d_previews: 0.0s [09:04] Saved high-quality screenshot: bas_relief_executed.png [09:04] [timing] final_screenshot: 0.6s [09:05] Capturing execution frames: da3_streaming.json [09:13] Frame 1 saved (frame_000.jpg, t=0.0s) [09:13] Validating workflow... [09:13] [ComfyUI] === /validate endpoint called === [09:13] [ComfyUI] Received JSON with keys: ['prompt'] [09:13] [ComfyUI] Prompt has 5 nodes [09:13] Queuing workflow for execution... [09:13] [ComfyUI] Node 2: DownloadAndLoadDepthAnythingV3Model [09:13] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [09:13] [ComfyUI] Node 3: LoadVideo [09:13] [ComfyUI] Inputs: {"file": "robot_unitree.mp4", "video-preview": ""} [09:13] [ComfyUI] Node 4: SaveVideo [09:13] [ComfyUI] Inputs: {"filename_prefix": "video/preview_da3", "format": "auto", "codec": "auto", "video": ["6", 0]} [09:13] [ComfyUI] Node 5: LoadSALADModel [09:13] [ComfyUI] Inputs: {} [09:13] [ComfyUI] Node 6: DepthAnythingV3_Streaming [09:13] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [09:13] [ComfyUI] 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 [09:13] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1418/ComfyUI', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [09:13] [ComfyUI] Generated prompt_id: 24b286a7-4fe3-4c19-9edc-569a2a45f8c7 [09:13] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [09:13] [ComfyUI] Calling execution.validate_prompt()... [09:13] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py', 'abstract://comfy_worker_56c06586f07c']... [09:13] [ComfyUI] Validation result: valid=True [09:13] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_56c06586f07c (abstract, no filesystem path) [09:13] [ComfyUI] === Validation PASSED === [09:13] [ComfyUI] got prompt [09:13] [ComfyUI] [comfy-env] Running LoadSALADModel: [09:13] [ComfyUI] [VRAM] Before LoadSALADModel: 747 / 24124 MB [09:13] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSALADModel.EXECUTE_NORMALIZED [09:13] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [09:13] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:13] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [09:13] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [09:13] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [09:16] Frame 2 saved (frame_001.jpg, t=2.5s) [09:16] [capture-periodic] freeze=4ms shot=200ms unfreeze=7ms saved=True [09:16] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [09:16] [ComfyUI] [SubprocessWorker] worker started/confirmed [09:16] [ComfyUI] [SubprocessWorker] sending request via socket... [09:16] [ComfyUI] [SubprocessWorker] call_id=27 sending call_method [09:17] [ComfyUI] [09:18] Frame 3 saved (frame_002.jpg, t=4.8s) [09:18] [capture-periodic] freeze=3ms shot=196ms unfreeze=6ms saved=True [09:19] [capture-loop] iter=50 t=6.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=5.0/31.2GB (16%) swap=0.0/32.0GB (0%) cpu=6% browser_rss=1.06GB [09:21] [ComfyUI] dino_salad.safetensors: 0%| | 0.00/352M [00:00 cpu: 563 / 24124 MB [09:21] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:21] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:21] [ComfyUI] [SubprocessWorker] call_id=28 sending model_to_device [09:21] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [09:21] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 563 / 24124 MB [09:21] [ComfyUI] [comfy-env] LoadSALADModel done (8.30s): result: NodeOutput [09:21] [ComfyUI] [VRAM] After LoadSALADModel: 563 / 24124 MB [09:21] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [09:21] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 563 / 24124 MB [09:21] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [09:21] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [09:21] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:21] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:21] [ComfyUI] [SubprocessWorker] worker started/confirmed [09:21] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [09:21] [ComfyUI] [SubprocessWorker] created 0 shm blocks [09:21] [ComfyUI] [SubprocessWorker] sending request via socket... [09:21] [ComfyUI] [SubprocessWorker] call_id=29 sending call_method [09:21] [ComfyUI] [SubprocessWorker] got response: ok [09:21] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (0.10s): result: NodeOutput [09:21] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 563 / 24124 MB [09:21] [ComfyUI] [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 [09:21] [ComfyUI] [VRAM] Before DepthAnythingV3_Streaming: 563 / 24124 MB [09:22] [ComfyUI] [SubprocessWorker] call_method: nodes.streaming.node.DepthAnythingV3_Streaming.EXECUTE_NORMALIZED [09:22] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [09:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:22] [ComfyUI] [SubprocessWorker] worker started/confirmed [09:22] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [09:22] [ComfyUI] [SubprocessWorker] created 1 shm blocks [09:22] [ComfyUI] [SubprocessWorker] sending request via socket... [09:22] [ComfyUI] [SubprocessWorker] call_id=30 sending call_method [09:22] Frame 4 saved (frame_003.jpg, t=9.4s) [09:22] [capture-periodic] freeze=2ms shot=161ms unfreeze=6ms saved=True [09:25] [capture-loop] iter=100 t=12.3s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=7.2/31.2GB (23%) swap=0.0/32.0GB (0%) cpu=6% browser_rss=1.05GB [09:26] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=30 [09:26] [ComfyUI] [comfy-env] VRAM request: 1.17GB, free before eviction: 24.71GB [09:26] [ComfyUI] [comfy-env] VRAM after eviction: 24.71GB [09:26] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +207MB (now 207MB) reserved=224MB peak=207MB [09:27] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +912MB (now 1119MB) reserved=1120MB peak=1119MB [09:30] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [09:30] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +548MB (now 1668MB) reserved=1696MB peak=1668MB [09:31] [capture-loop] iter=150 t=17.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=7.8/31.2GB (25%) swap=0.0/32.0GB (0%) cpu=6% browser_rss=1.05GB [09:31] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +967MB (now 2635MB) reserved=2688MB peak=2635MB [09:33] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 2986MB) reserved=4000MB peak=2986MB [09:34] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4928MB peak=3337MB [09:35] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4928MB peak=3688MB [09:36] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4257MB [09:37] [capture-loop] iter=200 t=23.8s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=7.8/31.2GB (25%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.97GB [09:38] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5536MB peak=4463MB [09:39] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7136MB peak=4556MB [09:39] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [09:40] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4160MB peak=4556MB [09:40] Frame 5 saved (frame_004.jpg, t=27.3s) [09:40] [capture-periodic] freeze=3ms shot=202ms unfreeze=7ms saved=True [09:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +701MB (now 3337MB) reserved=4320MB peak=4556MB [09:42] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4672MB peak=4556MB [09:42] [capture-loop] iter=250 t=29.6s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=7.9/31.2GB (25%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.97GB [09:43] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4556MB [09:46] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5376MB peak=4556MB [09:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7296MB peak=4556MB [09:47] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [09:48] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4160MB peak=4556MB [09:48] [capture-loop] iter=300 t=35.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=8.1/31.2GB (26%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.96GB [09:49] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +701MB (now 3337MB) reserved=4320MB peak=4556MB [09:49] Frame 6 saved (frame_005.jpg, t=36.4s) [09:49] [capture-periodic] freeze=3ms shot=198ms unfreeze=6ms saved=True [09:50] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4672MB peak=4556MB [09:51] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4556MB [09:53] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5696MB peak=4556MB [09:54] [capture-loop] iter=350 t=41.4s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=8.1/31.2GB (26%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.96GB [09:55] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7104MB peak=4556MB [09:55] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [09:56] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4160MB peak=4556MB [09:56] Frame 7 saved (frame_006.jpg, t=43.3s) [09:56] [capture-periodic] freeze=3ms shot=190ms unfreeze=7ms saved=True [09:57] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +701MB (now 3337MB) reserved=4320MB peak=4556MB [09:58] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4672MB peak=4556MB [09:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4603MB [10:00] [capture-loop] iter=400 t=47.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=8.3/31.2GB (26%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.97GB [10:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5568MB peak=4603MB [10:02] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7328MB peak=4603MB [10:03] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:03] Frame 8 saved (frame_007.jpg, t=50.2s) [10:03] [capture-periodic] freeze=3ms shot=190ms unfreeze=7ms saved=True [10:03] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4160MB peak=4603MB [10:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +701MB (now 3337MB) reserved=4320MB peak=4603MB [10:05] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4672MB peak=4603MB [10:06] [capture-loop] iter=450 t=53.1s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=8.5/31.2GB (27%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.97GB [10:07] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4603MB [10:09] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5728MB peak=4603MB [10:10] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7424MB peak=4603MB [10:10] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:11] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4160MB peak=4603MB [10:12] [capture-loop] iter=500 t=58.8s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=8.7/31.2GB (28%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.97GB [10:12] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +701MB (now 3337MB) reserved=4320MB peak=4603MB [10:12] Frame 9 saved (frame_008.jpg, t=59.4s) [10:12] [capture-periodic] freeze=3ms shot=194ms unfreeze=7ms saved=True [10:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [10:13] [ComfyUI] === WATCHDOG TICK 1 === [10:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] Thread 0x000072c3a6dbb640 (most recent call first): [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 359 in wait [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 655 in wait [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/tqdm/_monitor.py", line 60 in run [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1075 in _bootstrap_inner [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1032 in _bootstrap [10:13] [ComfyUI] [10:13] [ComfyUI] Thread 0x000072c55ffc2640 (most recent call first): [10:13] [ComfyUI] File "/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py", line 106 in _vram_poller [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1012 in run [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1075 in _bootstrap_inner [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1032 in _bootstrap [10:13] [ComfyUI] [10:13] [ComfyUI] Current thread 0x000072c5607c7640 (most recent call first): [10:13] [ComfyUI] File "/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py", line 52 in _watchdog [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1012 in run [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1075 in _bootstrap_inner [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1032 in _bootstrap [10:13] [ComfyUI] [10:13] [ComfyUI] Thread 0x000072c560dc2740 (most recent call first): [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 338 in forward [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 445 in forward [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 516 in attn_residual_func [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 521 in forward [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 791 in process_attention [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 750 in _get_intermediate_layers_not_chunked [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 800 in get_intermediate_layers [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 891 in forward [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1560 in forward [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 330 in _process_chunk [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 277 in run [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/node.py", line 249 in execute [10:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/comfy_api/latest/_io.py", line 1833 in EXECUTE_NORMALIZED [10:13] [ComfyUI] File "/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py", line 1762 in main [10:13] [ComfyUI] File "/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py", line 1807 in [10:13] [ComfyUI] [10:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] === END === [10:13] [ComfyUI] [10:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4672MB peak=4603MB [10:14] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4603MB [10:17] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5472MB peak=4603MB [10:18] [capture-loop] iter=550 t=64.8s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=8.7/31.2GB (28%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.97GB [10:18] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7104MB peak=4603MB [10:18] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:19] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4160MB peak=4603MB [10:19] Frame 10 saved (frame_009.jpg, t=66.3s) [10:19] [capture-periodic] freeze=3ms shot=172ms unfreeze=7ms saved=True [10:20] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +701MB (now 3337MB) reserved=4320MB peak=4603MB [10:21] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=4672MB peak=4603MB [10:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4480MB peak=4603MB [10:23] [capture-loop] iter=600 t=70.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=8.8/31.2GB (28%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.97GB [10:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5472MB peak=4603MB [10:26] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7264MB peak=4603MB [10:26] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:27] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +850MB (now 2367MB) reserved=3328MB peak=4603MB [10:28] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +467MB (now 2834MB) reserved=3776MB peak=4603MB [10:29] Frame 11 saved (frame_010.jpg, t=75.5s) [10:29] [capture-periodic] freeze=3ms shot=189ms unfreeze=6ms saved=True [10:29] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +514MB (now 3349MB) reserved=3776MB peak=4603MB [10:29] [capture-loop] iter=650 t=76.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=9.0/31.2GB (29%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.97GB [10:31] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:31] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2222MB (now 1128MB) reserved=1184MB peak=4603MB [10:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +214MB (now 1342MB) reserved=1408MB peak=4603MB [10:33] Frame 12 saved (frame_011.jpg, t=80.0s) [10:33] [capture-periodic] freeze=3ms shot=196ms unfreeze=16ms saved=True [10:34] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -215MB (now 1128MB) reserved=1632MB peak=4603MB [10:34] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:35] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +221MB (now 1350MB) reserved=1728MB peak=4603MB [10:35] [capture-loop] iter=700 t=82.3s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=9.9/31.2GB (32%) swap=0.0/32.0GB (0%) cpu=6% browser_rss=0.98GB [10:35] Frame 13 saved (frame_012.jpg, t=82.3s) [10:35] [capture-periodic] freeze=4ms shot=199ms unfreeze=8ms saved=True [10:36] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:36] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -222MB (now 1128MB) reserved=1760MB peak=4603MB [10:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +308MB (now 1437MB) reserved=1760MB peak=4603MB [10:38] Frame 14 saved (frame_013.jpg, t=84.6s) [10:38] [capture-periodic] freeze=3ms shot=224ms unfreeze=7ms saved=True [10:38] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:38] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -309MB (now 1128MB) reserved=1760MB peak=4603MB [10:39] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:40] Frame 15 saved (frame_014.jpg, t=87.0s) [10:40] [capture-periodic] freeze=3ms shot=203ms unfreeze=7ms saved=True [10:40] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +218MB (now 1347MB) reserved=1760MB peak=4603MB [10:41] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -219MB (now 1128MB) reserved=1760MB peak=4603MB [10:41] [capture-loop] iter=750 t=88.6s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=9.7/31.2GB (31%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.98GB [10:42] Frame 16 saved (frame_015.jpg, t=89.3s) [10:42] [capture-periodic] freeze=3ms shot=191ms unfreeze=7ms saved=True [10:42] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:43] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +318MB (now 1447MB) reserved=1760MB peak=4603MB [10:44] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: faiss not installed, skipping loop closure. pip install faiss-cpu [10:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -319MB (now 1128MB) reserved=1760MB peak=4603MB [10:45] Frame 17 saved (frame_016.jpg, t=91.6s) [10:45] [capture-periodic] freeze=3ms shot=189ms unfreeze=8ms saved=True [10:47] [capture-loop] iter=800 t=94.7s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=11.5/31.2GB (37%) swap=0.0/32.0GB (0%) cpu=6% browser_rss=0.98GB [10:48] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [10:49] Frame 18 saved (frame_017.jpg, t=96.2s) [10:49] [capture-periodic] freeze=3ms shot=191ms unfreeze=7ms saved=True [10:53] [capture-loop] iter=850 t=100.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=9.2/31.2GB (30%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.98GB [10:59] [capture-loop] iter=900 t=106.3s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=9.3/31.2GB (30%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.98GB [11:05] [capture-loop] iter=950 t=112.0s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=9.3/31.2GB (30%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.97GB [11:11] [capture-loop] iter=1000 t=117.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=9.3/31.2GB (30%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.98GB [11:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [11:13] [ComfyUI] === WATCHDOG TICK 2 === [11:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] Thread 0x000072c3a6dbb640 (most recent call first): [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 359 in wait [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 655 in wait [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/tqdm/_monitor.py", line 60 in run [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1075 in _bootstrap_inner [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1032 in _bootstrap [11:13] [ComfyUI] [11:13] [ComfyUI] Thread 0x000072c55ffc2640 (most recent call first): [11:13] [ComfyUI] File "/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py", line 106 in _vram_poller [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1012 in run [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1075 in _bootstrap_inner [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1032 in _bootstrap [11:13] [ComfyUI] [11:13] [ComfyUI] Current thread 0x000072c5607c7640 (most recent call first): [11:13] [ComfyUI] File "/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py", line 52 in _watchdog [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1012 in run [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1075 in _bootstrap_inner [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/threading.py", line 1032 in _bootstrap [11:13] [ComfyUI] [11:13] [ComfyUI] Thread 0x000072c560dc2740 (most recent call first): [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/zipfile/__init__.py", line 1235 in write [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/numpy/lib/_format_impl.py", line 777 in write_array [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/numpy/lib/_npyio_impl.py", line 786 in _savez [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages/numpy/lib/_npyio_impl.py", line 753 in savez_compressed [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/node.py", line 271 in execute [11:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1418/ComfyUI/comfy_api/latest/_io.py", line 1833 in EXECUTE_NORMALIZED [11:13] [ComfyUI] File "/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py", line 1762 in main [11:13] [ComfyUI] File "/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py", line 1807 in [11:13] [ComfyUI] [11:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] === END === [11:13] [ComfyUI] [11:16] [capture-loop] iter=1050 t=123.6s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=9.3/31.2GB (30%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.97GB [11:22] [capture-loop] iter=1100 t=129.4s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=9.3/31.2GB (30%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.98GB [11:28] [capture-loop] iter=1150 t=135.3s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=9.3/31.2GB (30%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=0.98GB [11:34] [capture-loop] iter=1200 t=141.0s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=11.0/31.2GB (35%) swap=0.0/32.0GB (0%) cpu=4% browser_rss=0.98GB [11:36] [ComfyUI] [SubprocessWorker] got response: ok [11:39] [ComfyUI] [comfy-env] Created 2 model patchers: ['DepthAnything3Net_1', 'VPRModel_2'] [11:39] [ComfyUI] [comfy-env] DepthAnythingV3_Streaming done (137.41s): result: NodeOutput [11:39] [ComfyUI] [VRAM] After DepthAnythingV3_Streaming: 2443 / 24124 MB [11:39] [ComfyUI] [VRAM] Loaded: SubprocessModel (335 MB), SubprocessModel (783 MB) [11:40] [capture-loop] iter=1250 t=146.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=10.1/31.2GB (32%) swap=0.0/32.0GB (0%) cpu=8% browser_rss=0.98GB [11:41] Frame 19 saved (frame_018.jpg, t=148.3s) [11:41] [capture-periodic] freeze=3ms shot=161ms unfreeze=6ms saved=True [11:43] [ComfyUI] Prompt executed in 150.28 seconds [11:44] Node executed (1 total), capturing... [11:44] Frame 20 saved (frame_019.jpg, t=151.0s) [11:44] [capture-node] freeze=4ms shot=204ms unfreeze=3ms saved=True [11:44] Execution complete (t=151.4s) [11:44] Captured 20 unique frames over 151.44s [11:44] [debug] iframes: 0 [11:44] [timing] trigger_3d_previews: 0.0s [11:47] Saved high-quality screenshot: da3_streaming_executed.png [11:47] [timing] final_screenshot: 0.5s [11:47] [ComfyUI] [comfy-env] [VRAM] Before offload 'VPRModel_2' (335 MB) -> cpu: 2443 / 24124 MB [11:47] Capturing execution frames: simple.json [11:47] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [11:47] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [11:47] [ComfyUI] [SubprocessWorker] call_id=31 sending model_to_device [11:47] [ComfyUI] [comfy-env] [VRAM] After offload 'VPRModel_2' (335 MB): 1547 / 24124 MB [11:47] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1547 / 24124 MB [11:47] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [11:47] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [11:47] [ComfyUI] [SubprocessWorker] call_id=32 sending model_to_device [11:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -336MB (now 792MB) reserved=864MB peak=4603MB [11:47] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 747 / 24124 MB [11:54] Frame 1 saved (frame_000.jpg, t=0.0s) [11:54] Validating workflow... [11:54] [ComfyUI] === /validate endpoint called === [11:54] [ComfyUI] Received JSON with keys: ['prompt'] [11:54] Queuing workflow for execution... [11:54] [ComfyUI] Prompt has 4 nodes [11:54] [ComfyUI] Node 2: LoadImage [11:54] [ComfyUI] Inputs: {"image": "bridge.jpg"} [11:54] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [11:54] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [11:54] [ComfyUI] Node 4: PreviewImage [11:54] [ComfyUI] Inputs: {"images": ["14", 0]} [11:54] [ComfyUI] Node 14: DepthAnything_V3 [11:54] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": true, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} [11:54] [ComfyUI] Generated prompt_id: 0073c930-6b79-4ab3-b4c6-7cb732e8e580 [11:54] [ComfyUI] Calling execution.validate_prompt()... [11:54] [ComfyUI] Validation result: valid=True [11:54] [ComfyUI] === Validation PASSED === [11:54] [ComfyUI] got prompt [11:54] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [11:54] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 747 / 24124 MB [11:54] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [11:54] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [11:54] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1418/ComfyUI', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [11:54] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [11:54] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [11:54] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [11:54] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py', 'abstract://comfy_worker_aa902efbe98d']... [11:54] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [11:54] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_aa902efbe98d (abstract, no filesystem path) [11:54] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [11:54] [ComfyUI] [comfy-env] Invalidated 2 stale model patchers (will be cleaned up during next unload) [11:56] Frame 2 saved (frame_001.jpg, t=2.4s) [11:56] [capture-periodic] freeze=3ms shot=207ms unfreeze=4ms saved=True [11:57] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [11:57] [ComfyUI] [SubprocessWorker] worker started/confirmed [11:57] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [11:57] [ComfyUI] [SubprocessWorker] created 0 shm blocks [11:57] [ComfyUI] [SubprocessWorker] sending request via socket... [11:57] [ComfyUI] [SubprocessWorker] call_id=33 sending call_method [11:57] [ComfyUI] [SubprocessWorker] got response: ok [11:57] [ComfyUI] [comfy-env] [VRAM] Before offload 'VPRModel_2' (335 MB) -> cpu: 563 / 24124 MB [11:57] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [11:57] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [11:57] [ComfyUI] [SubprocessWorker] call_id=34 sending model_to_device [11:57] [ComfyUI] Model 'VPRModel_2' gone from worker (restarted?), treating as offloaded [11:57] [ComfyUI] [comfy-env] [VRAM] After offload 'VPRModel_2' (335 MB): 563 / 24124 MB [11:57] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 563 / 24124 MB [11:58] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [11:58] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [11:58] [ComfyUI] [SubprocessWorker] call_id=35 sending model_to_device [11:58] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [11:58] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 563 / 24124 MB [11:58] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (3.53s): result: NodeOutput [11:58] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 563 / 24124 MB [11:58] [ComfyUI] [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 [11:58] [ComfyUI] [VRAM] Before DepthAnything_V3: 563 / 24124 MB [11:58] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [11:58] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [11:58] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [11:58] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [11:58] [ComfyUI] [SubprocessWorker] worker started/confirmed [11:58] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 683, 1024, 3]) [11:58] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [11:58] [ComfyUI] [SubprocessWorker] created 0 shm blocks [11:58] [ComfyUI] [SubprocessWorker] sending request via socket... [11:58] [ComfyUI] [SubprocessWorker] call_id=36 sending call_method [11:58] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [11:58] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 683, 1024, 3] [11:58] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 683, 1024, 3]) [11:59] Frame 3 saved (frame_002.jpg, t=4.8s) [11:59] [capture-periodic] freeze=3ms shot=197ms unfreeze=8ms saved=True [11:59] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=36 [11:59] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 24.71GB [11:59] [ComfyUI] [comfy-env] VRAM after eviction: 24.71GB [11:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +354MB (now 354MB) reserved=384MB peak=354MB [11:59] [ComfyUI] [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. [12:00] [capture-loop] iter=50 t=6.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=5.1/31.2GB (16%) swap=0.0/32.0GB (0%) cpu=7% browser_rss=1.07GB [12:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +498MB (now 853MB) reserved=864MB peak=853MB [12:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +636MB (now 1489MB) reserved=2528MB peak=1502MB [12:01] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=36 [12:02] [ComfyUI] [SubprocessWorker] got response: ok [12:02] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [12:02] [ComfyUI] [comfy-env] DepthAnything_V3 done (4.02s): result: NodeOutput [12:02] [ComfyUI] [VRAM] After DepthAnything_V3: 3175 / 24124 MB [12:02] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [12:02] [ComfyUI] Prompt executed in 7.66 seconds [12:02] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 3175 / 24124 MB [12:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [12:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [12:02] [ComfyUI] [SubprocessWorker] call_id=37 sending model_to_device [12:02] Node executed (1 total), capturing... [12:02] Frame 4 saved (frame_003.jpg, t=8.2s) [12:02] [capture-node] freeze=3ms shot=203ms unfreeze=0ms saved=True [12:02] Execution complete (t=8.2s) [12:02] Captured 4 unique frames over 8.54s [12:02] [debug] iframes: 0 [12:02] [timing] trigger_3d_previews: 0.0s [12:02] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 711 / 24124 MB [12:05] Saved high-quality screenshot: simple_executed.png [12:05] [timing] final_screenshot: 0.5s [12:05] Capturing execution frames: video_multiview_depth.json [12:12] Frame 1 saved (frame_000.jpg, t=0.0s) [12:12] Validating workflow... [12:12] [ComfyUI] === /validate endpoint called === [12:12] [ComfyUI] Received JSON with keys: ['prompt'] [12:12] [ComfyUI] Prompt has 9 nodes [12:12] Queuing workflow for execution... [12:12] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [12:12] [ComfyUI] Inputs: {"model": "da3_base.safetensors", "precision": "auto", "attention": "auto"} [12:12] [ComfyUI] Node 52: CreateVideo [12:12] [ComfyUI] Inputs: {"fps": 10, "images": ["62", 0]} [12:12] [ComfyUI] Node 53: CreateVideo [12:12] [ComfyUI] Inputs: {"fps": 10, "images": ["61", 0]} [12:12] [ComfyUI] Node 54: SaveVideo [12:12] [ComfyUI] Inputs: {"filename_prefix": "video/ComfyUI", "format": "auto", "codec": "auto", "video": ["52", 0]} [12:12] [ComfyUI] Node 55: SaveVideo [12:12] [ComfyUI] Inputs: {"filename_prefix": "video/ComfyUI", "format": "auto", "codec": "auto", "video": ["53", 0]} [12:12] [ComfyUI] Node 61: DepthAnything_V3 [12:12] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["71", 0]} [12:12] [ComfyUI] Node 62: DepthAnythingV3_MultiView [12:12] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["71", 0]} [12:12] [ComfyUI] Node 66: PreviewImage [12:12] [ComfyUI] Inputs: {"images": ["71", 0]} [12:12] [ComfyUI] Node 71: LoadImagesFromFolderKJ [12:12] [ComfyUI] Inputs: {"folder": "input/robotframes", "width": 1024, "height": 576, "keep_aspect_ratio": "crop", "image_load_cap": 0, "start_index": 0, "include_subfolders": false} [12:12] [ComfyUI] Generated prompt_id: 9fac7986-b0cd-41f3-8e8e-3f3e5846e3ea [12:12] [ComfyUI] Calling execution.validate_prompt()... [12:12] [ComfyUI] Validation result: valid=True [12:12] [ComfyUI] === Validation PASSED === [12:12] [ComfyUI] got prompt [12:13] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_base.safetensors', precision: 'auto', attention: 'auto' [12:13] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [12:13] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 711 / 24124 MB [12:13] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1418/ComfyUI', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.12/site-packages', '/workspaces/DepthAnythingV3-1418/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [12:13] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [12:13] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [12:13] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [12:13] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/workspaces/DepthAnythingV3-1418/ComfyUI/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_67kwy0_o/persistent_worker.py', 'abstract://comfy_worker_93b7c4c9b751']... [12:13] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [12:13] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_93b7c4c9b751 (abstract, no filesystem path) [12:13] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [12:13] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [12:13] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [12:13] Node executed (1 total), capturing... [12:14] Frame 2 saved (frame_001.jpg, t=1.7s) [12:14] [capture-node] freeze=3ms shot=197ms unfreeze=9ms saved=True [12:16] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [12:16] [ComfyUI] [SubprocessWorker] worker started/confirmed [12:16] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [12:17] [ComfyUI] [SubprocessWorker] created 0 shm blocks [12:17] [ComfyUI] [SubprocessWorker] sending request via socket... [12:17] [ComfyUI] [SubprocessWorker] call_id=38 sending call_method [12:17] [ComfyUI] [12:18] Frame 3 saved (frame_002.jpg, t=6.2s) [12:18] [capture-periodic] freeze=4ms shot=200ms unfreeze=7ms saved=True [12:19] [capture-loop] iter=50 t=6.7s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=3 ram=4.8/31.2GB (15%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=1.00GB [12:22] [ComfyUI] model.safetensors: 0%| | 0.00/542M [00:00 cpu: 563 / 24124 MB [12:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [12:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [12:25] [ComfyUI] [SubprocessWorker] call_id=39 sending model_to_device [12:25] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [12:25] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 563 / 24124 MB [12:25] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (11.38s): result: NodeOutput [12:25] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 563 / 24124 MB [12:25] [ComfyUI] [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 [12:25] [ComfyUI] [VRAM] Before DepthAnything_V3: 563 / 24124 MB [12:25] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [12:25] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [12:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [12:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [12:25] [ComfyUI] [SubprocessWorker] worker started/confirmed [12:25] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([13, 576, 1024, 3]) [12:25] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [12:25] [ComfyUI] [SubprocessWorker] created 0 shm blocks [12:25] [ComfyUI] [SubprocessWorker] sending request via socket... [12:25] [ComfyUI] [SubprocessWorker] call_id=40 sending call_method [12:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [12:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[13, 576, 1024, 3] [12:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([13, 576, 1024, 3]) [12:25] Frame 5 saved (frame_004.jpg, t=13.1s) [12:25] [capture-periodic] freeze=3ms shot=187ms unfreeze=9ms saved=True [12:26] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=40 [12:26] [ComfyUI] [comfy-env] VRAM request: 0.27GB, free before eviction: 24.71GB [12:26] [ComfyUI] [comfy-env] VRAM after eviction: 24.71GB [12:26] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +256MB (now 256MB) reserved=288MB peak=256MB [12:26] [ComfyUI] [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. [12:29] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +321MB (now 577MB) reserved=896MB peak=577MB [12:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [12:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [12:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [12:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [12:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [12:30] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [12:30] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -288MB (now 290MB) reserved=1056MB peak=621MB [12:30] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [12:30] Frame 6 saved (frame_005.jpg, t=17.7s) [12:30] [capture-periodic] freeze=5ms shot=215ms unfreeze=3ms saved=True [12:30] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [12:31] [capture-loop] iter=150 t=18.7s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=6.3/31.2GB (20%) swap=0.0/32.0GB (0%) cpu=5% browser_rss=1.00GB [12:32] [ComfyUI] [SubprocessWorker] got response: ok [12:32] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [12:32] [ComfyUI] [comfy-env] DepthAnything_V3 done (7.15s): result: NodeOutput [12:32] [ComfyUI] [VRAM] After DepthAnything_V3: 1767 / 24124 MB [12:32] [ComfyUI] [VRAM] Loaded: SubprocessModel (258 MB) [12:32] [ComfyUI] [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 [12:32] Frame 7 saved (frame_006.jpg, t=20.0s) [12:32] [capture-periodic] freeze=7ms shot=150ms unfreeze=13ms saved=True [12:32] [ComfyUI] [VRAM] Before DepthAnythingV3_MultiView: 1767 / 24124 MB [12:32] [ComfyUI] [VRAM] Loaded: SubprocessModel (258 MB) [12:32] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [12:32] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [12:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [12:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [12:32] [ComfyUI] [SubprocessWorker] worker started/confirmed [12:32] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([13, 576, 1024, 3]) [12:32] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [12:32] [ComfyUI] [SubprocessWorker] created 0 shm blocks [12:32] [ComfyUI] [SubprocessWorker] sending request via socket... [12:32] [ComfyUI] [SubprocessWorker] call_id=41 sending call_method [12:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [12:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[13, 576, 1024, 3] [12:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([13, 576, 1024, 3]) [12:32] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=41 [12:32] [ComfyUI] [comfy-env] VRAM request: 0.27GB, free before eviction: 23.44GB [12:32] [ComfyUI] [comfy-env] VRAM after eviction: 23.44GB [12:32] [ComfyUI] [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. [12:32] Node executed (2 total), capturing... [12:33] Frame 8 saved (frame_007.jpg, t=20.6s) [12:33] [capture-node] freeze=3ms shot=208ms unfreeze=4ms saved=True [12:33] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +420MB (now 711MB) reserved=1312MB peak=711MB [12:34] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +726MB (now 1437MB) reserved=2112MB peak=1437MB [12:35] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -784MB (now 653MB) reserved=2624MB peak=1437MB [12:35] Frame 9 saved (frame_008.jpg, t=22.9s) [12:35] [capture-periodic] freeze=3ms shot=205ms unfreeze=7ms saved=True [12:36] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -387MB (now 267MB) reserved=2624MB peak=1437MB [12:36] [ComfyUI] [SubprocessWorker] got response: ok [12:36] [ComfyUI] [comfy-env] DepthAnythingV3_MultiView done (3.85s): result: NodeOutput [12:36] [ComfyUI] [VRAM] After DepthAnythingV3_MultiView: 3271 / 24124 MB [12:36] [ComfyUI] [VRAM] Loaded: SubprocessModel (258 MB) [12:36] [ComfyUI] Prompt executed in 24.18 seconds [12:36] Node executed (3 total), capturing... [12:37] Frame 10 saved (frame_009.jpg, t=24.7s) [12:37] [capture-node] freeze=3ms shot=214ms unfreeze=5ms saved=True [12:37] Execution complete (t=25.1s) [12:37] Captured 10 unique frames over 25.14s [12:37] [debug] iframes: 0 [12:37] [timing] trigger_3d_previews: 0.0s [12:39] Saved high-quality screenshot: video_multiview_depth_executed.png [12:39] [timing] final_screenshot: 0.5s [12:39] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (258 MB) -> cpu: 3271 / 24124 MB [12:39] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [12:39] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [12:39] [ComfyUI] [SubprocessWorker] call_id=42 sending model_to_device [12:40] Results saved to /logs/DepthAnythingV3-1418/dev/linux-gpu/results.json [12:40] Model report: 9 files, 2.4 GB -> /logs/DepthAnythingV3-1418/dev/linux-gpu/models.json [12:40] Saved: /logs/DepthAnythingV3-1418/dev/linux-gpu/index.html [12:40] [EXECUTION] PASSED [12:40] linux: PASSED [12:40] Stopping ComfyUI server...