[00:00] Crash dump logging enabled: /logs/DepthAnythingV3-0833/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/DepthAnythingV3-0833/.venv --python 3.11 [00:00] Cloning ComfyUI (latest)... [00:00] Running: git clone --depth 1 https://github.com/comfyanonymous/ComfyUI.git /workspaces/DepthAnythingV3-0833/ComfyUI [00:01] Installing ComfyUI requirements... [00:01] Running: uv pip install --python /workspaces/DepthAnythingV3-0833/.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/DepthAnythingV3-0833/ComfyUI/requirements.txt [01:18] Installing custom node... [01:18] Copying ComfyUI-DepthAnythingV3 to custom_nodes/... [01:18] Installing node requirements... [01:18] Running: uv pip install --python /workspaces/DepthAnythingV3-0833/.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/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/requirements.txt [01:20] Running install.py... [01:20] Running: /workspaces/DepthAnythingV3-0833/.venv/bin/python /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/install.py [01:21] [01:21] Installing 3 node dependencies... [01:21] Cloning ComfyUI-VideoHelperSuite... [01:21] Installing requirements for ComfyUI-VideoHelperSuite... [01:23] Cloning ComfyUI-KJNodes... [01:26] Installing requirements for ComfyUI-KJNodes... [01:27] Cloning ComfyUI-GeometryPack... [01:32] Installing requirements for ComfyUI-GeometryPack... [01:33] Running install.py for ComfyUI-GeometryPack... [01:35] [comfy-env] _discover: scanning /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes [01:35] [comfy-env] _discover: ComfyUI-DepthAnythingV3 -> depthanythingv3-nodes (custom_nodes/ComfyUI-DepthAnythingV3/nodes/comfy-env.toml) [01:35] [comfy-env] _discover: ComfyUI-GeometryPack -> geometrypack-nodes (custom_nodes/ComfyUI-GeometryPack/nodes/comfy-env.toml) [01:35] [comfy-env] _discover: ComfyUI-KJNodes: no comfy-env.toml found [01:35] [comfy-env] _discover: ComfyUI-VideoHelperSuite: no comfy-env.toml found [01:35] [comfy-env] Workspace: /root/.ce [01:35] [comfy-env] ComfyUI: /workspaces/DepthAnythingV3-0833/ComfyUI [01:35] [comfy-env] Found 2 node config(s): [01:35] - depthanythingv3-nodes <- custom_nodes/ComfyUI-DepthAnythingV3/nodes/comfy-env.toml (python=host) [01:35] - geometrypack-nodes <- custom_nodes/ComfyUI-GeometryPack/nodes/comfy-env.toml (python=host) [01:35] [comfy-env] Bootstrap interpreter has python 3.11 + torch 2.11.0 (cu128). Looking for cuda-only wheels matching cu128/torch2.11/cp311. [01:35] [comfy-env] GPU: Detection: smi [01:35] Driver: 580.126.20 [01:35] CUDA: 13.0 [01:35] Recommended: CUDA 13.0 [01:35] [01:35] GPU 0: NVIDIA GeForce RTX 5060 (sm_120) [Blackwell] 8151MB [01:35] [comfy-env] Comfyui feature -> torch 2.11.0 from https://download.pytorch.org/whl/cu128 (CUDA 12.8 via bootstrap torch) [01:35] [comfy-env] cuda-wheels: 3 package(s) need a matched (cuda, torch, python) combo: ['flash_attn', 'sageattention', 'cumesh'] [01:35] [comfy-env] cuda-wheels tier 1 (bootstrap): probing cu12.8/torch2.11/cp311 [01:35] [cuda-wheels] Looking up flash_attn: cu128 torch2.11 cp311 manylinux linux [01:35] [cuda-wheels] Found: flash_attn-2.8.3+cu128torch2.11-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [01:35] [cuda-wheels] Looking up sageattention: cu128 torch2.11 cp311 manylinux linux [01:35] [cuda-wheels] Found: sageattention-2.2.0+cu128torch2.11-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [01:35] [cuda-wheels] Looking up cumesh: cu128 torch2.11 cp311 manylinux linux [01:36] [cuda-wheels] Found: cumesh-0.0.1+cu128torch2.11-cp311-cp311-manylinux_2_35_x86_64.whl [01:36] [comfy-env] cuda-wheels combo: cu12.8/torch2.11 (bootstrap matches; per-node envs will pin to this) [01:36] [comfy-env] Host glibc 2.35 -> system-requirements [01:36] [cuda-wheels] Looking up flash_attn: cu128 torch2.11 cp311 manylinux linux [01:36] [cuda-wheels] Found: flash_attn-2.8.3+cu128torch2.11-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [01:36] [cuda-wheels] Looking up sageattention: cu128 torch2.11 cp311 manylinux linux [01:36] [cuda-wheels] Found: sageattention-2.2.0+cu128torch2.11-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [01:36] [comfy-env] depthanythingv3-nodes: cuda-wheels deferred for post-pixi install (flash_attn, sageattention) [01:36] [cuda-wheels] Looking up cumesh: cu128 torch2.11 cp311 manylinux linux [01:36] [cuda-wheels] Found: cumesh-0.0.1+cu128torch2.11-cp311-cp311-manylinux_2_35_x86_64.whl [01:36] [comfy-env] geometrypack-nodes: cuda-wheels deferred for post-pixi install (cumesh) [01:36] Generated /root/.ce/pixi.toml [01:36] [comfy-env] Installing 2 environment(s): [01:36] - depthanythingv3-nodes (python=host, 11 pypi deps, 2 cuda wheels) [01:36] - geometrypack-nodes (python=host, 14 pypi deps, 1 cuda wheels) [01:36] [comfy-env] Running `pixi install -e depthanythingv3-nodes -e geometrypack-nodes`... [01:42] WARN Skipped running the post-link scripts because `run-post-link-scripts` = `false` [01:42] - bin/.librsvg-pre-unlink.sh [01:42] To enable them, run: [01:42] pixi config set --local run-post-link-scripts insecure [01:42] More info: [01:42] https://pixi.sh/latest/reference/pixi_configuration/#run-post-link-scripts [01:56] WARN Skipped running the post-link scripts because `run-post-link-scripts` = `false` [01:56] - bin/.librsvg-pre-unlink.sh [01:56] To enable them, run: [01:56] pixi config set --local run-post-link-scripts insecure [01:56] More info: [01:56] https://pixi.sh/latest/reference/pixi_configuration/#run-post-link-scripts [02:58] The following environments have been installed: depthanythingv3-nodes, geometrypack-nodes. [02:58] [comfy-env] depthanythingv3-nodes: installing cuda-wheels with --no-deps (flash_attn, sageattention) [02:58] Using Python 3.11.15 environment at: .pixi/envs/depthanythingv3-nodes [02:59] Resolved 2 packages in 1.50s [02:59] Downloading flash-attn (242.3MiB) [02:59] Downloading sageattention (53.2MiB) [03:01] Downloaded sageattention [03:05] Downloaded flash-attn [03:05] Prepared 2 packages in 5.49s [03:05] Installed 2 packages in 6ms [03:05] + 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-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl) [03:05] + sageattention==2.2.0+cu128torch2.11 (from https://github.com/PozzettiAndrea/cuda-wheels/releases/download/sageattention-latest/sageattention-2.2.0%2Bcu128torch2.11-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl) [03:05] [comfy-env] geometrypack-nodes: installing cuda-wheels with --no-deps (cumesh) [03:05] Using Python 3.11.15 environment at: .pixi/envs/geometrypack-nodes [03:06] Resolved 1 package in 739ms [03:06] Downloading cumesh (19.5MiB) [03:06] Downloaded cumesh [03:06] Prepared 1 package in 337ms [03:06] Installed 1 package in 2ms [03:06] + cumesh==0.0.1+cu128torch2.11 (from https://github.com/PozzettiAndrea/cuda-wheels/releases/download/cumesh-latest/cumesh-0.0.1%2Bcu128torch2.11-cp311-cp311-manylinux_2_35_x86_64.whl) [03:06] [comfy-env] Recorded install hash 2fe352e17cb2 -> /root/.ce/install.hash [03:06] [comfy-env] Install log: /root/.ce/install.log [03:06] [03:06] Installation complete! [03:06] [03:06] [requirements] Re-installing main package requirements... [03:06] Installing requirements for ComfyUI-DepthAnythingV3... [03:06] [comfy-env] _discover: scanning /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes [03:06] [comfy-env] _discover: ComfyUI-DepthAnythingV3 -> depthanythingv3-nodes (custom_nodes/ComfyUI-DepthAnythingV3/nodes/comfy-env.toml) [03:06] [comfy-env] _discover: ComfyUI-GeometryPack -> geometrypack-nodes (custom_nodes/ComfyUI-GeometryPack/nodes/comfy-env.toml) [03:06] [comfy-env] _discover: ComfyUI-KJNodes: no comfy-env.toml found [03:06] [comfy-env] _discover: ComfyUI-VideoHelperSuite: no comfy-env.toml found [03:06] [comfy-env] Workspace inputs unchanged (hash 2fe352e17cb2) -- skipping install. Delete /root/.ce/install.hash to force. [03:06] [03:06] Installation complete! [03:06] Installing 3 node dependency(ies)... [03:06] ComfyUI-VideoHelperSuite from Kosinkadink/ComfyUI-VideoHelperSuite [03:06] ComfyUI-VideoHelperSuite already exists, skipping... [03:06] ComfyUI-KJNodes from kijai/ComfyUI-KJNodes [03:06] ComfyUI-KJNodes already exists, skipping... [03:06] ComfyUI-GeometryPack from PozzettiAndrea/ComfyUI-GeometryPack [03:06] ComfyUI-GeometryPack already exists, skipping... [03:06] Installing validation endpoint... [03:06] Cloning PozzettiAndrea/ComfyUI-validate-endpoint... [03:06] Running: git clone --depth 1 https://github.com/PozzettiAndrea/ComfyUI-validate-endpoint.git /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-validate-endpoint [03:07] CUDA packages absent (will mock): flash_attn, sageattention [03:07] [INSTALL] PASSED [03:07] [03:07] [3/5] REGISTRATION [03:07] ---------------------------------------- [03:07] [DEBUG] server=None, server_url=None, api=None [03:07] Starting ComfyUI server... [03:07] Starting ComfyUI server on port 41899... [03:07] CUDA mock packages: flash_attn, sageattention [03:07] Starting ComfyUI server on port 41899... [03:07] Waiting for server to be ready (timeout: 600s)... [03:08] [ComfyUI] setup plugin alembic.autogenerate.schemas [03:08] [ComfyUI] setup plugin alembic.autogenerate.tables [03:08] [ComfyUI] setup plugin alembic.autogenerate.types [03:08] [ComfyUI] setup plugin alembic.autogenerate.constraints [03:08] [ComfyUI] setup plugin alembic.autogenerate.defaults [03:08] [ComfyUI] setup plugin alembic.autogenerate.comments [03:08] [ComfyUI] [comfy-env] ComfyUI-GeometryPack: 1 isolation env(s): [03:08] [ComfyUI] [comfy-env] nodes -> /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-GeometryPack/nodes [03:08] [ComfyUI] [comfy-env] Workspace: /root/.ce [03:08] [ComfyUI] [comfy-env] env: /root/.ce/.pixi/envs/geometrypack-nodes [OK] [03:08] [ComfyUI] [comfy-env] prestartup complete [03:08] [ComfyUI] [comfy-env] ComfyUI-DepthAnythingV3: 1 isolation env(s): [03:08] [ComfyUI] [comfy-env] nodes -> /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes [03:08] [ComfyUI] [comfy-env] env: /root/.ce/.pixi/envs/depthanythingv3-nodes [OK] [03:08] [ComfyUI] [comfy-env] prestartup complete [03:08] [ComfyUI] [03:08] [ComfyUI] Prestartup times for custom nodes: [03:08] [ComfyUI] 0.0 seconds: /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 [03:08] [ComfyUI] 0.2 seconds: /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-GeometryPack [03:08] [ComfyUI] [03:13] [ComfyUI] WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [03:13] [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']} [03:13] [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']} [03:13] [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']} [03:13] [ComfyUI] Checkpoint files will always be loaded safely. [03:13] [ComfyUI] Total VRAM 7704 MB, total RAM 32011 MB [03:13] [ComfyUI] pytorch version: 2.11.0+cu128 [03:13] [ComfyUI] Set vram state to: NORMAL_VRAM [03:13] [ComfyUI] Device: cuda:0 NVIDIA GeForce RTX 5060 : cudaMallocAsync [03:13] [ComfyUI] Using async weight offloading with 2 streams [03:13] [ComfyUI] Enabled pinned memory 28810.0 [03:13] [ComfyUI] Using pytorch attention [03:17] [ComfyUI] aimdo: /project/src-posix/cuda-funchooks.c:52:DEBUG:aimdo_setup_hooks: hooks successfully installed [03:17] [ComfyUI] aimdo: /project/src/control.c:151:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 5060 (VRAM: 7703 MB) [03:17] [ComfyUI] DynamicVRAM support detected and enabled [03:17] [ComfyUI] Python version: 3.11.15 (main, May 8 2026, 18:33:10) [Clang 22.1.3 ] [03:17] [ComfyUI] ComfyUI version: 0.21.0 [03:17] [ComfyUI] comfy-aimdo version: 0.3.0 [03:17] [ComfyUI] comfy-kitchen version: 0.2.8 [03:17] [ComfyUI] ****** User settings have been changed to be stored on the server instead of browser storage. ****** [03:17] [ComfyUI] ****** For multi-user setups add the --multi-user CLI argument to enable multiple user profiles. ****** [03:17] [ComfyUI] ComfyUI frontend version: 1.43.18 [03:17] [ComfyUI] [Prompt Server] web root: /workspaces/DepthAnythingV3-0833/.venv/lib/python3.11/site-packages/comfyui_frontend_package/static [03:17] [ComfyUI] Asset seeder disabled [03:19] [ComfyUI] loading... [03:19] [ComfyUI] calling register_nodes [03:19] [ComfyUI] [comfy-env] Version: 0.3.87 [03:19] [ComfyUI] [comfy-env] register_nodes: ComfyUI-GeometryPack [03:19] [ComfyUI] [comfy-env] ComfyUI source dir: /workspaces/DepthAnythingV3-0833/ComfyUI [03:19] [ComfyUI] [comfy-env] Found 1 isolation env(s) [03:19] [ComfyUI] [comfy-env] Scanning nodes metadata (isolation root)... [03:19] [ComfyUI] [comfy-env] Metadata scan: /root/.pixi/bin/pixi run --as-is --manifest-path /root/.ce/pixi.toml -e geometrypack-nodes python /tmp/comfy_meta_2acwb9mx.py /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-GeometryPack nodes /tmp/comfy_meta_out_148e05_y.pkl [03:19] [ComfyUI] [comfy-env] Scan env PATH for nodes: [03:19] [ComfyUI] [comfy-env] [0] /root/.local/bin [03:19] [ComfyUI] [comfy-env] [1] /usr/local/nvidia/bin [03:19] [ComfyUI] [comfy-env] [2] /usr/local/cuda/bin [03:19] [ComfyUI] [comfy-env] [3] /usr/local/sbin [03:19] [ComfyUI] [comfy-env] [4] /usr/local/bin [03:19] [ComfyUI] [comfy-env] [5] /usr/sbin [03:19] [ComfyUI] [comfy-env] [6] /usr/bin [03:19] [ComfyUI] [comfy-env] [7] /sbin [03:19] [ComfyUI] [comfy-env] [8] /bin [03:24] [ComfyUI] [comfy-env] Metadata scan stderr for nodes: [03:24] [ComfyUI] [comfy-env] [meta-scan] importing nodes from /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-GeometryPack [03:24] [ComfyUI] [comfy-env] ERROR:root:Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [03:24] [ComfyUI] [comfy-env] [meta-scan] import OK [03:24] [ComfyUI] [comfy-env] Scanned nodes: 125 nodes (4.9s) [03:24] [ComfyUI] [comfy-env] Scanned nodes root: 125 nodes (4.9s) [03:24] [ComfyUI] [comfy-env] Imported nodes root: 125 nodes (isolation) [03:24] [ComfyUI] [comfy-env] Registered 125 total nodes [03:24] [ComfyUI] [comfy-env] Version: 0.3.87 [03:24] [ComfyUI] [comfy-env] register_nodes: ComfyUI-DepthAnythingV3 [03:24] [ComfyUI] [comfy-env] ComfyUI source dir: /workspaces/DepthAnythingV3-0833/ComfyUI [03:24] [ComfyUI] [comfy-env] Found 1 isolation env(s) [03:24] [ComfyUI] [comfy-env] Scanning nodes metadata (isolation root)... [03:24] [ComfyUI] [comfy-env] Metadata scan: /root/.pixi/bin/pixi run --as-is --manifest-path /root/.ce/pixi.toml -e depthanythingv3-nodes python /tmp/comfy_meta_i5ndghff.py /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 nodes /tmp/comfy_meta_out_7kjbubcq.pkl [03:24] [ComfyUI] [comfy-env] Scan env PATH for nodes: [03:24] [ComfyUI] [comfy-env] [0] /root/.local/bin [03:24] [ComfyUI] [comfy-env] [1] /usr/local/nvidia/bin [03:24] [ComfyUI] [comfy-env] [2] /usr/local/cuda/bin [03:24] [ComfyUI] [comfy-env] [3] /usr/local/sbin [03:24] [ComfyUI] [comfy-env] [4] /usr/local/bin [03:24] [ComfyUI] [comfy-env] [5] /usr/sbin [03:24] [ComfyUI] [comfy-env] [6] /usr/bin [03:24] [ComfyUI] [comfy-env] [7] /sbin [03:24] [ComfyUI] [comfy-env] [8] /bin [03:27] [ComfyUI] [comfy-env] Metadata scan stderr for nodes: [03:27] [ComfyUI] [comfy-env] [meta-scan] importing nodes from /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 [03:27] [ComfyUI] [comfy-env] ERROR:root:Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [03:27] [ComfyUI] [comfy-env] [meta-scan] import OK [03:27] [ComfyUI] [comfy-env] Scanned nodes: 15 nodes (2.7s) [03:27] [ComfyUI] [comfy-env] Scanned nodes root: 15 nodes (2.7s) [03:27] [ComfyUI] [comfy-env] Imported nodes root: 15 nodes (isolation) [03:27] [ComfyUI] [comfy-env] Registered 15 total nodes [03:27] [ComfyUI] [03:27] [ComfyUI] Import times for custom nodes: [03:27] [ComfyUI] 0.0 seconds: /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/websocket_image_save.py [03:27] [ComfyUI] 0.0 seconds: /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-validate-endpoint [03:27] [ComfyUI] 0.1 seconds: /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite [03:27] [ComfyUI] 0.1 seconds: /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-KJNodes [03:27] [ComfyUI] 2.7 seconds: /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 [03:27] [ComfyUI] 5.0 seconds: /workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-GeometryPack [03:27] [ComfyUI] [03:27] [ComfyUI] Context impl SQLiteImpl. [03:27] [ComfyUI] Will assume non-transactional DDL. [03:27] [ComfyUI] Context impl SQLiteImpl. [03:27] [ComfyUI] Will assume non-transactional DDL. [03:27] [ComfyUI] Running upgrade -> 0001_assets, Initial assets schema [03:27] [ComfyUI] Revision ID: 0001_assets [03:27] [ComfyUI] Revises: None [03:27] [ComfyUI] Create Date: 2025-12-10 00:00:00 [03:27] [ComfyUI] Running upgrade 0001_assets -> 0002_merge_to_asset_references, Merge AssetInfo and AssetCacheState into unified asset_references table. [03:27] [ComfyUI] Running upgrade 0002_merge_to_asset_references -> 0003_add_metadata_job_id, Add system_metadata and job_id columns to asset_references. [03:27] [ComfyUI] Change preview_id FK from assets.id to asset_references.id. [03:27] [ComfyUI] Database upgraded from None to 0003_add_metadata_job_id [03:27] [ComfyUI] Starting server [03:27] [ComfyUI] [03:27] [ComfyUI] To see the GUI go to: http://127.0.0.1:41899 [03:28] Server responding, waiting for nodes to load... [03:48] Server is ready! [03:48] Checking for import errors in server logs... [03:48] No import errors detected [03:48] Found 1129 registered nodes [03:48] [REGISTRATION] PASSED [03:48] [03:48] [4/5] INSTANTIATION [03:48] ---------------------------------------- [03:48] [DEBUG] server=, server_url=None, api= [03:48] Testing node constructors... [03:48] All 15 node(s) instantiated successfully! [03:48] [INSTANTIATION] PASSED [03:48] [03:48] [5/5] EXECUTION [03:48] ---------------------------------------- [03:48] [DEBUG] server=, server_url=None, api= [03:48] GPU runner - will execute 7 workflow(s) [03:48] Running 7 workflow(s) (all with videos)... [03:48] Installing screenshot dependencies (playwright, pillow)... [03:50] Packages installed, downloading chromium browser... [04:06] Screenshot dependencies installed successfully [04:06] Starting headless browser... [04:06] Installing Vulkan stack (apt)... [04:06] Vulkan install error: [Errno 2] No such file or directory: 'sudo' [04:06] GPU detected (no Vulkan) -- using ANGLE/OpenGL rendering [04:06] Capturing execution frames: advanced.json [04:08] [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. [04:13] Frame 1 saved (frame_000.jpg, t=0.0s) [04:13] Validating workflow... [04:13] [ComfyUI] === /validate endpoint called === [04:13] [ComfyUI] Received JSON with keys: ['prompt'] [04:13] [ComfyUI] Prompt has 11 nodes [04:13] [ComfyUI] Node 2: LoadImage [04:13] [ComfyUI] Inputs: {"image": "bridge.jpg"} [04:13] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [04:13] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [04:13] [ComfyUI] Node 4: PreviewImage [04:13] Queuing workflow for execution... [04:13] [ComfyUI] Inputs: {"images": ["12", 0]} [04:13] [ComfyUI] Node 6: PreviewImage [04:13] [ComfyUI] Inputs: {"images": ["12", 1]} [04:13] [ComfyUI] Node 7: PreviewImage [04:13] [ComfyUI] Inputs: {"images": ["12", 2]} [04:13] [ComfyUI] Node 8: PreviewImage [04:13] [ComfyUI] Inputs: {"images": ["12", 3]} [04:13] [ComfyUI] Node 9: PreviewAny [04:13] [ComfyUI] Inputs: {"source": ["12", 6]} [04:13] [ComfyUI] Node 10: PreviewAny [04:13] [ComfyUI] Inputs: {"source": ["12", 5]} [04:13] [ComfyUI] Node 11: MaskPreview [04:13] [ComfyUI] Inputs: {"mask": ["12", 7]} [04:13] [ComfyUI] Node 12: DepthAnything_V3 [04:13] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} [04:13] [ComfyUI] Node 13: PreviewImage [04:13] [ComfyUI] Inputs: {"images": ["12", 4]} [04:13] [ComfyUI] Generated prompt_id: 9a933b05-39a5-4044-a8ac-5d53d8415cd9 [04:13] [ComfyUI] Calling execution.validate_prompt()... [04:13] [ComfyUI] Validation result: valid=True [04:13] [ComfyUI] === Validation PASSED === [04:13] [ComfyUI] got prompt [04:13] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [04:13] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 152 / 7703 MB [04:13] [ComfyUI] [comfy-env] SubprocessWorker: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [04:13] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [04:13] [ComfyUI] [comfy-env] env_vars: {'COMFYUI_BASE': '/workspaces/DepthAnythingV3-0833/ComfyUI'} [04:13] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [04:13] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [04:13] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-0833/ComfyUI', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [04:13] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [04:13] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py', 'abstract://comfy_worker_d17b54bec5e8']... [04:13] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_d17b54bec5e8 (abstract, no filesystem path) [04:14] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [04:14] [ComfyUI] [SubprocessWorker] worker started/confirmed [04:14] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [04:14] [ComfyUI] [SubprocessWorker] created 0 shm blocks [04:14] [ComfyUI] [SubprocessWorker] sending request via socket... [04:14] [ComfyUI] [SubprocessWorker] call_id=1 sending call_method [04:15] [ComfyUI] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. [04:15] [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. [04:15] Frame 2 saved (frame_001.jpg, t=2.4s) [04:15] [capture-periodic] freeze=2ms shot=139ms unfreeze=4ms saved=True [04:15] [ComfyUI] [04:17] Frame 3 saved (frame_002.jpg, t=4.7s) [04:17] [capture-periodic] freeze=2ms shot=128ms unfreeze=5ms saved=True [04:18] [ComfyUI] model.safetensors: 0%| | 0.00/1.64G [00:00 cpu: 2905 / 7703 MB [04:55] Capturing execution frames: advanced_3d.json [04:55] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [04:55] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [04:55] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [04:55] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [04:55] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-0833/ComfyUI', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [04:55] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [04:55] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [04:55] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py', 'abstract://comfy_worker_72a8523aba85']... [04:55] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_72a8523aba85 (abstract, no filesystem path) [04:56] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [04:56] [ComfyUI] [SubprocessWorker] call_id=3 sending model_to_device [04:56] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [04:56] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 269 / 7703 MB [05:00] Frame 1 saved (frame_000.jpg, t=0.0s) [05:00] Validating workflow... [05:00] [ComfyUI] === /validate endpoint called === [05:00] [ComfyUI] Received JSON with keys: ['prompt'] [05:00] [ComfyUI] Prompt has 6 nodes [05:00] [ComfyUI] Node 2: LoadImage [05:00] [ComfyUI] Inputs: {"image": "kaffi.jpg"} [05:00] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [05:00] Queuing workflow for execution... [05:00] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [05:00] [ComfyUI] Node 21: DepthAnything_V3 [05:00] [ComfyUI] Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} [05:00] [ComfyUI] Node 22: DA3_ToPointCloud [05:00] [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 [05:00] [ComfyUI] Node 23: DA3_SavePointCloud [05:00] [ComfyUI] Inputs: {"filename_prefix": "pointcloud", "pointcloud": ["22", 0]} [05:00] [ComfyUI] Node 25: DA3_PreviewPointCloud [05:00] [ComfyUI] Inputs: {"file_path": ["23", 0], "color_mode": "RGB", "preview_vtk": ""} [05:00] [ComfyUI] Generated prompt_id: bd4171b0-85bf-447f-8407-3f0590cf72e8 [05:00] [ComfyUI] Calling execution.validate_prompt()... [05:00] [ComfyUI] Validation result: valid=True [05:00] [ComfyUI] === Validation PASSED === [05:00] [ComfyUI] got prompt [05:00] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [05:00] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 269 / 7703 MB [05:00] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [05:00] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:00] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:00] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:00] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:00] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:00] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:00] [ComfyUI] [SubprocessWorker] sending request via socket... [05:00] [ComfyUI] [SubprocessWorker] call_id=4 sending call_method [05:01] [ComfyUI] [SubprocessWorker] got response: ok [05:01] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 269 / 7703 MB [05:01] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:01] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:01] [ComfyUI] [SubprocessWorker] call_id=5 sending model_to_device [05:01] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [05:01] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 269 / 7703 MB [05:01] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (0.13s): result: NodeOutput [05:01] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 269 / 7703 MB [05:01] [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 [05:01] [ComfyUI] [VRAM] Before DepthAnything_V3: 269 / 7703 MB [05:01] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [05:01] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:01] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:01] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:01] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:01] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 533, 800, 3]) [05:01] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:01] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:01] [ComfyUI] [SubprocessWorker] sending request via socket... [05:01] [ComfyUI] [SubprocessWorker] call_id=6 sending call_method [05:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 533, 800, 3] [05:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 533, 800, 3]) [05:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [05:03] Frame 2 saved (frame_001.jpg, t=2.3s) [05:03] [capture-periodic] freeze=2ms shot=142ms unfreeze=5ms saved=True [05:03] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=6 [05:03] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 7.80GB [05:03] [ComfyUI] [comfy-env] VRAM after eviction: 7.80GB [05:03] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +314MB (now 314MB) reserved=320MB peak=314MB [05:04] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=6 [05:04] [ComfyUI] [SubprocessWorker] got response: ok [05:04] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [05:04] [ComfyUI] [comfy-env] DepthAnything_V3 done (3.52s): result: NodeOutput [05:04] [ComfyUI] [VRAM] After DepthAnything_V3: 2263 / 7703 MB [05:04] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:04] [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 [05:04] [ComfyUI] [VRAM] Before DA3_ToPointCloud: 2263 / 7703 MB [05:04] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:04] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_ToPointCloud.EXECUTE_NORMALIZED [05:04] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:04] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:04] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:04] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:04] [ComfyUI] [comfy-env] PRE-SERIALIZE 'depth_raw' shape: torch.Size([1, 532, 800, 3]) [05:04] [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 532, 800, 3]) [05:04] [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 532, 800]) [05:04] [ComfyUI] [comfy-env] PRE-SERIALIZE 'source_image' shape: torch.Size([1, 532, 800, 3]) [05:04] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:04] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:04] [ComfyUI] [SubprocessWorker] sending request via socket... [05:04] [ComfyUI] [SubprocessWorker] call_id=7 sending call_method [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800]) [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [05:04] [ComfyUI] [SubprocessWorker] got response: ok [05:04] [ComfyUI] [comfy-env] DA3_ToPointCloud done (0.07s): result: NodeOutput [05:04] [ComfyUI] [VRAM] After DA3_ToPointCloud: 2263 / 7703 MB [05:04] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:04] [ComfyUI] [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [05:04] [ComfyUI] [VRAM] Before DA3_SavePointCloud: 2263 / 7703 MB [05:04] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:04] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [05:04] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:04] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:04] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:04] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:04] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:04] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:04] [ComfyUI] [SubprocessWorker] sending request via socket... [05:04] [ComfyUI] [SubprocessWorker] call_id=8 sending call_method [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +478MB (now 792MB) reserved=1888MB peak=1022MB [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311395, 3] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311395, 3]) [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311395] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311395]) [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311395, 3] [05:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311395, 3]) [05:05] Frame 3 saved (frame_002.jpg, t=4.5s) [05:05] [capture-periodic] freeze=2ms shot=138ms unfreeze=4ms saved=True [05:06] [capture-loop] iter=50 t=5.7s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=4.6/31.3GB (15%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.92GB [05:06] [ComfyUI] [SubprocessWorker] got response: ok [05:06] [ComfyUI] [comfy-env] DA3_SavePointCloud done (2.05s): result: NodeOutput [05:06] [ComfyUI] [VRAM] After DA3_SavePointCloud: 2263 / 7703 MB [05:06] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:06] [ComfyUI] [comfy-env] Running DA3_PreviewPointCloud: file_path: '/workspaces/DepthAnythingV3-0833/ComfyUI/output/pointclo..., color_mode: 'RGB' [05:06] [ComfyUI] [VRAM] Before DA3_PreviewPointCloud: 2263 / 7703 MB [05:06] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:06] [ComfyUI] [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [05:06] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:06] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:06] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:06] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:06] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:06] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:06] [ComfyUI] [SubprocessWorker] sending request via socket... [05:06] [ComfyUI] [SubprocessWorker] call_id=9 sending call_method [05:06] [ComfyUI] [SubprocessWorker] got response: ok [05:06] [ComfyUI] [comfy-env] DA3_PreviewPointCloud done (0.01s): result: NodeOutput [05:06] [ComfyUI] [VRAM] After DA3_PreviewPointCloud: 2263 / 7703 MB [05:06] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:06] [ComfyUI] Prompt executed in 5.80 seconds [05:06] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 2263 / 7703 MB [05:06] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:06] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:06] [ComfyUI] [SubprocessWorker] call_id=10 sending model_to_device [05:06] Node executed (2 total), capturing... [05:06] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -296MB (now 497MB) reserved=1888MB peak=1022MB [05:07] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 439 / 7703 MB [05:08] Frame 4 saved (frame_003.jpg, t=6.2s) [05:08] [capture-node] freeze=1229ms shot=106ms unfreeze=0ms saved=True [05:08] Execution complete (t=6.2s) [05:08] Captured 4 unique frames over 7.59s [05:08] [debug] iframes: 1 [05:08] [debug] iframe[0]: src=http://127.0.0.1:41899/extensions/ComfyUI-GeometryPack/viewer_vtk.html?v=1778661, canvas=486x394, rafFrozen=True [05:08] [timing] trigger_3d_previews: 0.0s [05:10] Saved high-quality screenshot: advanced_3d_executed.png [05:10] [timing] final_screenshot: 0.2s [05:10] Capturing execution frames: advanced_3d_multiview.json [05:16] Frame 1 saved (frame_000.jpg, t=0.0s) [05:16] Validating workflow... [05:16] [ComfyUI] === /validate endpoint called === [05:16] [ComfyUI] Received JSON with keys: ['prompt'] [05:16] [ComfyUI] Prompt has 8 nodes [05:16] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [05:16] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [05:16] [ComfyUI] Node 21: LoadImageDataSetFromFolder [05:16] [ComfyUI] Inputs: {"folder": "SOH"} [05:16] Queuing workflow for execution... [05:16] [ComfyUI] Node 27: PreviewImage [05:16] [ComfyUI] Inputs: {"images": ["21", 0]} [05:16] [ComfyUI] Node 38: DA3_MultiViewPointCloud [05:16] [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": [05:16] [ComfyUI] Node 39: DepthAnythingV3_MultiView [05:16] [ComfyUI] Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["21", 0]} [05:16] [ComfyUI] Node 44: DA3_SavePointCloud [05:16] [ComfyUI] Inputs: {"filename_prefix": "pointcloud", "pointcloud": ["38", 0]} [05:16] [ComfyUI] Node 45: PreviewAny [05:16] [ComfyUI] Inputs: {"source": ["44", 0]} [05:16] [ComfyUI] Node 48: DA3_PreviewPointCloud [05:16] [ComfyUI] Inputs: {"file_path": ["44", 0], "color_mode": "RGB", "preview_vtk": ""} [05:16] [ComfyUI] Generated prompt_id: 8cb9ec38-5636-4728-9492-ad1a939eeb15 [05:16] [ComfyUI] Calling execution.validate_prompt()... [05:16] [ComfyUI] Validation result: valid=True [05:16] [ComfyUI] === Validation PASSED === [05:16] [ComfyUI] got prompt [05:16] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [05:16] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 439 / 7703 MB [05:16] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [05:16] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:16] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:16] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [05:16] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [05:16] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [05:16] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [05:16] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-0833/ComfyUI', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [05:16] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [05:16] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py', 'abstract://comfy_worker_f43ac019b666']... [05:16] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_f43ac019b666 (abstract, no filesystem path) [05:16] Node executed (1 total), capturing... [05:16] Frame 2 saved (frame_001.jpg, t=0.6s) [05:16] [capture-node] freeze=2ms shot=137ms unfreeze=6ms saved=True [05:17] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [05:17] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:17] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:17] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:17] [ComfyUI] [SubprocessWorker] sending request via socket... [05:17] [ComfyUI] [SubprocessWorker] call_id=11 sending call_method [05:17] [ComfyUI] [SubprocessWorker] got response: ok [05:17] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 269 / 7703 MB [05:17] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:17] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:17] [ComfyUI] [SubprocessWorker] call_id=12 sending model_to_device [05:17] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [05:17] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 269 / 7703 MB [05:17] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (1.61s): result: NodeOutput [05:17] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 269 / 7703 MB [05:17] [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 [05:17] [ComfyUI] [VRAM] Before DepthAnythingV3_MultiView: 269 / 7703 MB [05:17] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [05:17] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:17] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:17] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:17] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:17] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [05:17] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:17] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:17] [ComfyUI] [SubprocessWorker] sending request via socket... [05:17] [ComfyUI] [SubprocessWorker] call_id=13 sending call_method [05:17] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:17] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [05:17] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [05:18] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [05:19] Frame 3 saved (frame_002.jpg, t=2.9s) [05:19] [capture-periodic] freeze=2ms shot=139ms unfreeze=6ms saved=True [05:20] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=13 [05:20] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 7.80GB [05:20] [ComfyUI] [comfy-env] VRAM after eviction: 7.80GB [05:20] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +202MB (now 202MB) reserved=224MB peak=202MB [05:21] Frame 4 saved (frame_003.jpg, t=5.1s) [05:21] [capture-periodic] freeze=2ms shot=136ms unfreeze=6ms saved=True [05:21] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +741MB (now 943MB) reserved=2848MB peak=1240MB [05:21] [ComfyUI] [SubprocessWorker] got response: ok [05:21] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [05:21] [ComfyUI] [comfy-env] DepthAnythingV3_MultiView done (3.72s): result: NodeOutput [05:21] [ComfyUI] [VRAM] After DepthAnythingV3_MultiView: 3223 / 7703 MB [05:21] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:21] [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 [05:21] [ComfyUI] [VRAM] Before DepthAnythingV3_MultiView: 3223 / 7703 MB [05:21] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:21] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [05:21] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:21] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:21] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:21] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:21] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [05:21] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:21] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:21] [ComfyUI] [SubprocessWorker] sending request via socket... [05:21] [ComfyUI] [SubprocessWorker] call_id=14 sending call_method [05:21] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:21] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [05:21] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [05:21] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=14 [05:21] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 4.70GB [05:21] [ComfyUI] [comfy-env] VRAM after eviction: 4.70GB [05:22] [capture-loop] iter=50 t=6.1s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=2 ram=4.7/31.3GB (15%) swap=0.0/32.0GB (0%) cpu=15% browser_rss=0.99GB [05:22] [ComfyUI] [SubprocessWorker] got response: ok [05:22] [ComfyUI] [comfy-env] DepthAnythingV3_MultiView done (0.52s): result: NodeOutput [05:22] [ComfyUI] [VRAM] After DepthAnythingV3_MultiView: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [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 [05:22] [ComfyUI] [VRAM] Before DA3_MultiViewPointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DA3_MultiViewPointCloud.EXECUTE_NORMALIZED [05:22] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:22] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:22] [ComfyUI] [comfy-env] PRE-SERIALIZE 'depths' shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 680, 1208]) [05:22] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:22] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:22] [ComfyUI] [SubprocessWorker] sending request via socket... [05:22] [ComfyUI] [SubprocessWorker] call_id=15 sending call_method [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208]) [05:22] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=15 [05:22] [ComfyUI] [SubprocessWorker] got response: ok [05:22] [ComfyUI] [comfy-env] DA3_MultiViewPointCloud done (0.06s): result: NodeOutput [05:22] [ComfyUI] [VRAM] After DA3_MultiViewPointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [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 [05:22] [ComfyUI] [VRAM] Before DA3_MultiViewPointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DA3_MultiViewPointCloud.EXECUTE_NORMALIZED [05:22] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:22] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:22] [ComfyUI] [comfy-env] PRE-SERIALIZE 'depths' shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 680, 1208]) [05:22] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:22] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:22] [ComfyUI] [SubprocessWorker] sending request via socket... [05:22] [ComfyUI] [SubprocessWorker] call_id=16 sending call_method [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208]) [05:22] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=16 [05:22] [ComfyUI] [SubprocessWorker] got response: ok [05:22] [ComfyUI] [comfy-env] DA3_MultiViewPointCloud done (0.08s): result: NodeOutput [05:22] [ComfyUI] [VRAM] After DA3_MultiViewPointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [05:22] [ComfyUI] [VRAM] Before DA3_SavePointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [05:22] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:22] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:22] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:22] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:22] [ComfyUI] [SubprocessWorker] sending request via socket... [05:22] [ComfyUI] [SubprocessWorker] call_id=17 sending call_method [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18819, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18819, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18819, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18819, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18819] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18819]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[18819] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([18819]) [05:22] [ComfyUI] [SubprocessWorker] got response: ok [05:22] [ComfyUI] [comfy-env] DA3_SavePointCloud done (0.16s): result: NodeOutput [05:22] [ComfyUI] [VRAM] After DA3_SavePointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [05:22] [ComfyUI] [VRAM] Before DA3_SavePointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [05:22] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:22] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:22] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:22] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:22] [ComfyUI] [SubprocessWorker] sending request via socket... [05:22] [ComfyUI] [SubprocessWorker] call_id=18 sending call_method [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20447, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20447, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20447, 3] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20447, 3]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20447] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20447]) [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[20447] [05:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([20447]) [05:22] [ComfyUI] [SubprocessWorker] got response: ok [05:22] [ComfyUI] [comfy-env] DA3_SavePointCloud done (0.17s): result: NodeOutput [05:22] [ComfyUI] [VRAM] After DA3_SavePointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [comfy-env] Running DA3_PreviewPointCloud: file_path: '/workspaces/DepthAnythingV3-0833/ComfyUI/output/pointclo..., color_mode: 'RGB' [05:22] [ComfyUI] [VRAM] Before DA3_PreviewPointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [05:22] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:22] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:22] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:22] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:22] [ComfyUI] [SubprocessWorker] sending request via socket... [05:22] [ComfyUI] [SubprocessWorker] call_id=19 sending call_method [05:22] [ComfyUI] [SubprocessWorker] got response: ok [05:22] [ComfyUI] [comfy-env] DA3_PreviewPointCloud done (0.01s): result: NodeOutput [05:22] [ComfyUI] [VRAM] After DA3_PreviewPointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [comfy-env] Running DA3_PreviewPointCloud: file_path: '/workspaces/DepthAnythingV3-0833/ComfyUI/output/pointclo..., color_mode: 'RGB' [05:22] [ComfyUI] [VRAM] Before DA3_PreviewPointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [05:22] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:22] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:22] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:22] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:22] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:22] [ComfyUI] [SubprocessWorker] sending request via socket... [05:22] [ComfyUI] [SubprocessWorker] call_id=20 sending call_method [05:22] [ComfyUI] [SubprocessWorker] got response: ok [05:22] [ComfyUI] [comfy-env] DA3_PreviewPointCloud done (0.01s): result: NodeOutput [05:22] [ComfyUI] [VRAM] After DA3_PreviewPointCloud: 3127 / 7703 MB [05:22] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:22] [ComfyUI] Prompt executed in 6.52 seconds [05:22] Node executed (4 total), capturing... [05:23] Frame 5 saved (frame_004.jpg, t=6.9s) [05:23] [capture-node] freeze=2ms shot=206ms unfreeze=0ms saved=True [05:23] Execution complete (t=6.9s) [05:23] Captured 5 unique frames over 7.18s [05:23] [debug] iframes: 1 [05:23] [debug] iframe[0]: src=http://127.0.0.1:41899/extensions/ComfyUI-GeometryPack/viewer_vtk.html?v=1778661, canvas=486x394, rafFrozen=True [05:23] [timing] trigger_3d_previews: 0.0s [05:25] Saved high-quality screenshot: advanced_3d_multiview_executed.png [05:25] [timing] final_screenshot: 0.2s [05:25] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 3127 / 7703 MB [05:25] Capturing execution frames: bas_relief.json [05:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:25] [ComfyUI] [SubprocessWorker] call_id=21 sending model_to_device [05:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -281MB (now 663MB) reserved=2752MB peak=1240MB [05:25] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 439 / 7703 MB [05:31] Frame 1 saved (frame_000.jpg, t=0.0s) [05:31] Validating workflow... [05:31] [ComfyUI] === /validate endpoint called === [05:31] [ComfyUI] Received JSON with keys: ['prompt'] [05:31] [ComfyUI] Prompt has 6 nodes [05:31] [ComfyUI] Node 2: LoadImage [05:31] [ComfyUI] Inputs: {"image": "bas_relief.png"} [05:31] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [05:31] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [05:31] Queuing workflow for execution... [05:31] [ComfyUI] Node 21: DepthAnything_V3 [05:31] [ComfyUI] Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": true, "da3_model": ["3", 0], "images": ["2", 0]} [05:31] [ComfyUI] Node 27: PreviewImage [05:31] [ComfyUI] Inputs: {"images": ["21", 2]} [05:31] [ComfyUI] Node 30: Preview3D [05:31] [ComfyUI] Inputs: {"model_file": ["32", 0], "image": ""} [05:31] [ComfyUI] Node 32: DA3_ToMesh [05:31] [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 [05:31] [ComfyUI] Generated prompt_id: fc4550ad-c2a2-4107-8e0c-8bee7e49336e [05:31] [ComfyUI] Calling execution.validate_prompt()... [05:31] [ComfyUI] Validation result: valid=True [05:31] [ComfyUI] === Validation PASSED === [05:31] [ComfyUI] got prompt [05:31] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [05:31] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 439 / 7703 MB [05:31] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [05:31] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:31] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:31] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [05:31] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [05:31] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [05:31] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [05:31] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-0833/ComfyUI', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [05:31] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [05:31] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py', 'abstract://comfy_worker_fa19b95090b4']... [05:31] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_fa19b95090b4 (abstract, no filesystem path) [05:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [05:33] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:33] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:33] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:33] [ComfyUI] [SubprocessWorker] sending request via socket... [05:33] [ComfyUI] [SubprocessWorker] call_id=22 sending call_method [05:33] [ComfyUI] [SubprocessWorker] got response: ok [05:33] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 269 / 7703 MB [05:33] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:33] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:33] [ComfyUI] [SubprocessWorker] call_id=23 sending model_to_device [05:33] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [05:33] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 269 / 7703 MB [05:33] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (1.61s): result: NodeOutput [05:33] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 269 / 7703 MB [05:33] [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 [05:33] [ComfyUI] [VRAM] Before DepthAnything_V3: 269 / 7703 MB [05:33] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [05:33] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:33] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:33] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:33] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:33] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 2000, 1336, 3]) [05:33] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:33] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:33] [ComfyUI] [SubprocessWorker] sending request via socket... [05:33] [ComfyUI] [SubprocessWorker] call_id=24 sending call_method [05:33] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:33] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2000, 1336, 3] [05:33] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2000, 1336, 3]) [05:33] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [05:33] Frame 2 saved (frame_001.jpg, t=2.3s) [05:33] [capture-periodic] freeze=1ms shot=165ms unfreeze=2ms saved=True [05:35] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=24 [05:35] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 7.80GB [05:35] [ComfyUI] [comfy-env] VRAM after eviction: 7.80GB [05:35] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +218MB (now 218MB) reserved=224MB peak=218MB [05:35] Frame 3 saved (frame_002.jpg, t=4.6s) [05:35] [capture-periodic] freeze=2ms shot=171ms unfreeze=6ms saved=True [05:36] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +962MB (now 1180MB) reserved=1440MB peak=1180MB [05:37] [capture-loop] iter=50 t=5.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=4.6/31.3GB (15%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.93GB [05:37] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=24 [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -388MB (now 793MB) reserved=6976MB peak=3480MB [05:37] [ComfyUI] [SubprocessWorker] got response: ok [05:37] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [05:37] [ComfyUI] [comfy-env] DepthAnything_V3 done (4.70s): result: NodeOutput [05:37] [ComfyUI] [VRAM] After DepthAnything_V3: 7351 / 7703 MB [05:37] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:37] [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 [05:37] [ComfyUI] [VRAM] Before DA3_ToMesh: 7351 / 7703 MB [05:37] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:37] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_ToMesh.EXECUTE_NORMALIZED [05:37] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [05:37] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:37] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:37] [ComfyUI] [SubprocessWorker] worker started/confirmed [05:37] [ComfyUI] [comfy-env] PRE-SERIALIZE 'depth_raw' shape: torch.Size([1, 2002, 1330, 3]) [05:37] [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 2002, 1330, 3]) [05:37] [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 2002, 1330]) [05:37] [ComfyUI] [comfy-env] PRE-SERIALIZE 'source_image' shape: torch.Size([1, 2002, 1330, 3]) [05:37] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [05:37] [ComfyUI] [SubprocessWorker] created 0 shm blocks [05:37] [ComfyUI] [SubprocessWorker] sending request via socket... [05:37] [ComfyUI] [SubprocessWorker] call_id=25 sending call_method [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330, 3] [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330, 3]) [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330, 3] [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330, 3]) [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330] [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330]) [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2002, 1330, 3] [05:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2002, 1330, 3]) [05:38] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: pyfqmr not installed, skipping decimation. Install with: pip install pyfqmr [05:38] Frame 4 saved (frame_003.jpg, t=6.9s) [05:38] [capture-periodic] freeze=2ms shot=159ms unfreeze=3ms saved=True [05:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: pygltflib is required for material post-processing. Install with: pip install pygltflib. Mesh may appear dark or single-sided. [05:41] [ComfyUI] [SubprocessWorker] got response: ok [05:41] [ComfyUI] [comfy-env] DA3_ToMesh done (3.36s): result: NodeOutput [05:41] [ComfyUI] [VRAM] After DA3_ToMesh: 7419 / 7703 MB [05:41] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [05:41] Node executed (1 total), capturing... [05:41] [ComfyUI] Prompt executed in 10.07 seconds [05:41] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 7419 / 7703 MB [05:41] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [05:41] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [05:41] [ComfyUI] [SubprocessWorker] call_id=26 sending model_to_device [05:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -322MB (now 471MB) reserved=6976MB peak=3480MB [05:41] Frame 5 saved (frame_004.jpg, t=10.3s) [05:41] [capture-node] freeze=2ms shot=264ms unfreeze=22ms saved=True [05:41] Node executed (3 total), capturing... [05:41] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 507 / 7703 MB [05:42] Frame 6 saved (frame_005.jpg, t=10.9s) [05:42] [capture-node] freeze=2ms shot=272ms unfreeze=0ms saved=True [05:42] Execution complete (t=11.0s) [05:42] [3d-wait] Phase 1: Waiting for 'Loading 3D Model' text to disappear... [06:42] [3d-wait] Phase 1 exception after 60.0s: Page.wait_for_function: Timeout 60000ms exceeded. [06:42] [3d-wait] Phase 2: iframes=0 [06:42] [3d-wait] Total 3D wait: 60.0s [06:42] Captured 6 unique frames over 71.48s [06:42] [debug] iframes: 0 [06:42] [timing] trigger_3d_previews: 0.0s [06:45] Saved high-quality screenshot: bas_relief_executed.png [06:45] [timing] final_screenshot: 0.5s [06:45] Capturing execution frames: da3_streaming.json [06:51] Frame 1 saved (frame_000.jpg, t=0.0s) [06:51] Validating workflow... [06:51] [ComfyUI] === /validate endpoint called === [06:51] [ComfyUI] Received JSON with keys: ['prompt'] [06:51] [ComfyUI] Prompt has 5 nodes [06:51] [ComfyUI] Node 2: DownloadAndLoadDepthAnythingV3Model [06:51] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [06:51] [ComfyUI] Node 3: LoadVideo [06:51] Queuing workflow for execution... [06:51] [ComfyUI] Inputs: {"file": "robot_unitree.mp4", "video-preview": ""} [06:51] [ComfyUI] Node 4: SaveVideo [06:51] [ComfyUI] Inputs: {"filename_prefix": "video/preview_da3", "format": "auto", "codec": "auto", "video": ["6", 0]} [06:51] [ComfyUI] Node 5: LoadSALADModel [06:51] [ComfyUI] Inputs: {} [06:51] [ComfyUI] Node 6: DepthAnythingV3_Streaming [06:51] [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 [06:51] [ComfyUI] Generated prompt_id: 9b9ee04f-b168-4d74-bfa5-d7c00b97597d [06:51] [ComfyUI] Calling execution.validate_prompt()... [06:51] [ComfyUI] Validation result: valid=True [06:51] [ComfyUI] === Validation PASSED === [06:51] [ComfyUI] got prompt [06:51] [ComfyUI] [comfy-env] Running LoadSALADModel: [06:51] [ComfyUI] [VRAM] Before LoadSALADModel: 507 / 7703 MB [06:51] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSALADModel.EXECUTE_NORMALIZED [06:51] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [06:51] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [06:51] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [06:51] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [06:51] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [06:51] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:51] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-0833/ComfyUI', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [06:51] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:51] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py', 'abstract://comfy_worker_903775a8d6fb']... [06:51] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_903775a8d6fb (abstract, no filesystem path) [06:52] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [06:53] [ComfyUI] [SubprocessWorker] worker started/confirmed [06:53] [ComfyUI] [SubprocessWorker] sending request via socket... [06:53] [ComfyUI] [SubprocessWorker] call_id=27 sending call_method [06:53] [ComfyUI] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. [06:53] [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. [06:53] [ComfyUI] [06:53] Frame 2 saved (frame_001.jpg, t=2.3s) [06:53] [capture-periodic] freeze=2ms shot=128ms unfreeze=5ms saved=True [06:56] Frame 3 saved (frame_002.jpg, t=4.6s) [06:56] [capture-periodic] freeze=2ms shot=136ms unfreeze=2ms saved=True [06:56] [ComfyUI] dino_salad.safetensors: 0%| | 0.00/352M [00:00 cpu: 269 / 7703 MB [07:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:02] [ComfyUI] [SubprocessWorker] call_id=28 sending model_to_device [07:02] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [07:02] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 269 / 7703 MB [07:02] [ComfyUI] [comfy-env] LoadSALADModel done (11.33s): result: NodeOutput [07:02] [ComfyUI] [VRAM] After LoadSALADModel: 269 / 7703 MB [07:02] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [07:02] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 269 / 7703 MB [07:02] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [07:02] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:02] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:02] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:02] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:02] [ComfyUI] [SubprocessWorker] sending request via socket... [07:02] [ComfyUI] [SubprocessWorker] call_id=29 sending call_method [07:02] [ComfyUI] [SubprocessWorker] got response: ok [07:02] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (0.02s): result: NodeOutput [07:02] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 269 / 7703 MB [07:02] [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 [07:02] [ComfyUI] [VRAM] Before DepthAnythingV3_Streaming: 269 / 7703 MB [07:02] [ComfyUI] [SubprocessWorker] call_method: nodes.streaming.node.DepthAnythingV3_Streaming.EXECUTE_NORMALIZED [07:02] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:02] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:02] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:02] [ComfyUI] [SubprocessWorker] created 1 shm blocks [07:02] [ComfyUI] [SubprocessWorker] sending request via socket... [07:02] [ComfyUI] [SubprocessWorker] call_id=30 sending call_method [07:02] Frame 6 saved (frame_005.jpg, t=11.4s) [07:02] [capture-periodic] freeze=2ms shot=146ms unfreeze=2ms saved=True [07:05] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [07:05] Frame 7 saved (frame_006.jpg, t=13.7s) [07:05] [capture-periodic] freeze=1ms shot=79ms unfreeze=5ms saved=True [07:06] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=30 [07:06] [ComfyUI] [comfy-env] VRAM request: 1.17GB, free before eviction: 7.80GB [07:06] [ComfyUI] [comfy-env] VRAM after eviction: 7.80GB [07:06] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +324MB (now 324MB) reserved=352MB peak=324MB [07:07] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +795MB (now 1119MB) reserved=1120MB peak=1119MB [07:08] [capture-loop] iter=150 t=16.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=7.7/31.3GB (24%) swap=0.0/32.0GB (0%) cpu=14% browser_rss=1.07GB [07:10] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [07:10] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +276MB (now 1395MB) reserved=1408MB peak=1395MB [07:11] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1240MB (now 2635MB) reserved=4032MB peak=2635MB [07:12] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 2986MB) reserved=4480MB peak=3249MB [07:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4928MB peak=3337MB [07:13] [capture-loop] iter=200 t=22.4s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=7.3/31.3GB (23%) swap=0.0/32.0GB (0%) cpu=13% browser_rss=1.04GB [07:14] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=5280MB peak=3688MB [07:15] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +579MB (now 4267MB) reserved=4512MB peak=4267MB [07:18] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4473MB) reserved=5504MB peak=4473MB [07:19] [capture-loop] iter=250 t=28.0s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=7.1/31.3GB (23%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.96GB [07:20] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2957MB (now 1517MB) reserved=7136MB peak=4556MB [07:20] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [07:20] Frame 8 saved (frame_007.jpg, t=29.1s) [07:20] [capture-periodic] freeze=2ms shot=139ms unfreeze=3ms saved=True [07:21] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4064MB peak=4556MB [07:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 2986MB) reserved=4416MB peak=4556MB [07:23] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4832MB peak=4556MB [07:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=5120MB peak=4556MB [07:24] [capture-loop] iter=300 t=33.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=1 ram=7.3/31.3GB (23%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.96GB [07:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +579MB (now 4267MB) reserved=4608MB peak=4556MB [07:28] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4473MB) reserved=5536MB peak=4556MB [07:30] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2957MB (now 1517MB) reserved=7264MB peak=4556MB [07:30] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [07:30] [capture-loop] iter=350 t=39.1s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=7.5/31.3GB (24%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.96GB [07:31] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4064MB peak=4556MB [07:31] Frame 9 saved (frame_008.jpg, t=40.2s) [07:31] [capture-periodic] freeze=2ms shot=115ms unfreeze=1ms saved=True [07:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 2986MB) reserved=4416MB peak=4556MB [07:33] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4832MB peak=4556MB [07:34] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +877MB (now 4214MB) reserved=5120MB peak=4556MB [07:35] [capture-loop] iter=400 t=44.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=7.5/31.3GB (24%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.96GB [07:37] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +207MB (now 4422MB) reserved=5248MB peak=4556MB [07:39] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2906MB (now 1517MB) reserved=7264MB peak=4556MB [07:39] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [07:40] Frame 10 saved (frame_009.jpg, t=49.1s) [07:40] [capture-periodic] freeze=2ms shot=130ms unfreeze=3ms saved=True [07:40] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4064MB peak=4556MB [07:41] [capture-loop] iter=450 t=50.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=7.7/31.3GB (25%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.96GB [07:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 2986MB) reserved=4416MB peak=4556MB [07:42] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4832MB peak=4556MB [07:43] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=5120MB peak=4556MB [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +568MB (now 4257MB) reserved=4544MB peak=4556MB [07:46] [capture-loop] iter=500 t=55.6s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=7.7/31.3GB (25%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.96GB [07:48] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4463MB) reserved=5440MB peak=4556MB [07:49] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2947MB (now 1517MB) reserved=7264MB peak=4556MB [07:49] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [07:50] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4064MB peak=4556MB [07:51] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 2986MB) reserved=4416MB peak=4556MB [07:51] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [07:51] [ComfyUI] === WATCHDOG TICK 1 === [07:51] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] Thread 0x00007f9d01447640 (most recent call first): [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 331 in wait [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 629 in wait [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/tqdm/_monitor.py", line 60 in run [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1045 in _bootstrap_inner [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1002 in _bootstrap [07:51] [ComfyUI] [07:51] [ComfyUI] Thread 0x00007fa0ab220640 (most recent call first): [07:51] [ComfyUI] File "/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py", line 106 in _vram_poller [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 982 in run [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1045 in _bootstrap_inner [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1002 in _bootstrap [07:51] [ComfyUI] [07:51] [ComfyUI] Current thread 0x00007fa0aba25640 (most recent call first): [07:51] [ComfyUI] File "/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py", line 52 in _watchdog [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 982 in run [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1045 in _bootstrap_inner [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1002 in _bootstrap [07:51] [ComfyUI] [07:51] [ComfyUI] Thread 0x00007fa0ac045740 (most recent call first): [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 338 in forward [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 445 in forward [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 516 in attn_residual_func [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 521 in forward [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 791 in process_attention [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 750 in _get_intermediate_layers_not_chunked [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 800 in get_intermediate_layers [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 891 in forward [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1560 in forward [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790 in _call_impl [07:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779 in _wrapped_call_impl [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 330 in _process_chunk [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 277 in run [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/node.py", line 249 in execute [07:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/comfy_api/latest/_io.py", line 1833 in EXECUTE_NORMALIZED [07:51] [ComfyUI] File "/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py", line 1762 in main [07:51] [ComfyUI] File "/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py", line 1807 in [07:51] [ComfyUI] [07:51] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] === END === [07:51] [ComfyUI] [07:51] Frame 11 saved (frame_010.jpg, t=60.2s) [07:51] [capture-periodic] freeze=2ms shot=135ms unfreeze=5ms saved=True [07:52] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4832MB peak=4556MB [07:52] [capture-loop] iter=550 t=61.3s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=7.9/31.3GB (25%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.97GB [07:53] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=5120MB peak=4556MB [07:54] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +579MB (now 4267MB) reserved=4608MB peak=4556MB [07:57] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4473MB) reserved=5472MB peak=4556MB [07:58] [capture-loop] iter=600 t=66.7s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=7.9/31.3GB (25%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.97GB [07:59] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2957MB (now 1517MB) reserved=7264MB peak=4556MB [07:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:00] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4064MB peak=4556MB [08:00] Frame 12 saved (frame_011.jpg, t=69.0s) [08:00] [capture-periodic] freeze=2ms shot=127ms unfreeze=5ms saved=True [08:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 2986MB) reserved=4416MB peak=4556MB [08:02] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4832MB peak=4556MB [08:03] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=5120MB peak=4556MB [08:03] [capture-loop] iter=650 t=72.3s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=1 ram=8.1/31.3GB (26%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.97GB [08:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +579MB (now 4267MB) reserved=4608MB peak=4556MB [08:07] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4473MB) reserved=5472MB peak=4556MB [08:09] [capture-loop] iter=700 t=77.8s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=8.2/31.3GB (26%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.97GB [08:09] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2957MB (now 1517MB) reserved=7264MB peak=4556MB [08:09] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:09] Frame 13 saved (frame_012.jpg, t=77.9s) [08:09] [capture-periodic] freeze=2ms shot=130ms unfreeze=5ms saved=True [08:10] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +1118MB (now 2635MB) reserved=4064MB peak=4556MB [08:11] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 2986MB) reserved=4416MB peak=4556MB [08:12] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3337MB) reserved=4832MB peak=4556MB [08:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +350MB (now 3688MB) reserved=5120MB peak=4556MB [08:14] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +579MB (now 4267MB) reserved=4608MB peak=4556MB [08:14] [capture-loop] iter=750 t=83.4s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=8.3/31.3GB (26%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.97GB [08:17] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 4473MB) reserved=5472MB peak=4556MB [08:18] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -2957MB (now 1517MB) reserved=7264MB peak=4556MB [08:18] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:19] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +850MB (now 2367MB) reserved=3200MB peak=4556MB [08:20] [capture-loop] iter=800 t=88.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=8.5/31.3GB (27%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.97GB [08:20] Frame 14 saved (frame_013.jpg, t=89.0s) [08:20] [capture-periodic] freeze=1ms shot=138ms unfreeze=5ms saved=True [08:21] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +467MB (now 2834MB) reserved=4000MB peak=4556MB [08:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +473MB (now 3308MB) reserved=3648MB peak=4556MB [08:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -1921MB (now 1387MB) reserved=5504MB peak=4556MB [08:24] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:25] [capture-loop] iter=850 t=94.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=8.9/31.3GB (29%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.97GB [08:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -259MB (now 1128MB) reserved=1216MB peak=4556MB [08:26] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +343MB (now 1471MB) reserved=1536MB peak=4556MB [08:27] Frame 15 saved (frame_014.jpg, t=95.7s) [08:27] [capture-periodic] freeze=2ms shot=139ms unfreeze=3ms saved=True [08:28] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -344MB (now 1128MB) reserved=1632MB peak=4556MB [08:28] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:29] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +221MB (now 1349MB) reserved=1632MB peak=4556MB [08:29] Frame 16 saved (frame_015.jpg, t=97.9s) [08:29] [capture-periodic] freeze=2ms shot=137ms unfreeze=6ms saved=True [08:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:30] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -222MB (now 1128MB) reserved=1728MB peak=4556MB [08:30] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:31] [capture-loop] iter=900 t=100.1s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=9.0/31.3GB (29%) swap=0.0/32.0GB (0%) cpu=13% browser_rss=0.97GB [08:31] Frame 17 saved (frame_016.jpg, t=100.2s) [08:31] [capture-periodic] freeze=2ms shot=132ms unfreeze=3ms saved=True [08:31] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +315MB (now 1444MB) reserved=1728MB peak=4556MB [08:32] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -316MB (now 1128MB) reserved=1728MB peak=4556MB [08:33] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:34] Frame 18 saved (frame_017.jpg, t=102.5s) [08:34] [capture-periodic] freeze=1ms shot=140ms unfreeze=5ms saved=True [08:34] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +257MB (now 1385MB) reserved=1728MB peak=4556MB [08:35] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:35] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -258MB (now 1128MB) reserved=1728MB peak=4556MB [08:36] Frame 19 saved (frame_018.jpg, t=104.8s) [08:36] [capture-periodic] freeze=2ms shot=140ms unfreeze=7ms saved=True [08:36] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:36] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: faiss not installed, skipping loop closure. pip install faiss-cpu [08:37] [capture-loop] iter=950 t=105.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=9.0/31.3GB (29%) swap=0.0/32.0GB (0%) cpu=13% browser_rss=0.97GB [08:38] Frame 20 saved (frame_019.jpg, t=107.0s) [08:38] [capture-periodic] freeze=1ms shot=141ms unfreeze=4ms saved=True [08:40] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=30 [08:40] Frame 21 saved (frame_020.jpg, t=109.3s) [08:40] [capture-periodic] freeze=1ms shot=130ms unfreeze=5ms saved=True [08:42] [capture-loop] iter=1000 t=111.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=8.4/31.3GB (27%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.98GB [08:48] [capture-loop] iter=1050 t=117.0s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=8.3/31.3GB (27%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.97GB [08:51] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [08:51] [ComfyUI] === WATCHDOG TICK 2 === [08:51] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] Thread 0x00007f9d01447640 (most recent call first): [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 331 in wait [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 629 in wait [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/tqdm/_monitor.py", line 60 in run [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1045 in _bootstrap_inner [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1002 in _bootstrap [08:51] [ComfyUI] [08:51] [ComfyUI] Thread 0x00007fa0ab220640 (most recent call first): [08:51] [ComfyUI] File "/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py", line 106 in _vram_poller [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 982 in run [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1045 in _bootstrap_inner [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1002 in _bootstrap [08:51] [ComfyUI] [08:51] [ComfyUI] Current thread 0x00007fa0aba25640 (most recent call first): [08:51] [ComfyUI] File "/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py", line 52 in _watchdog [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 982 in run [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1045 in _bootstrap_inner [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/threading.py", line 1002 in _bootstrap [08:51] [ComfyUI] [08:51] [ComfyUI] Thread 0x00007fa0ac045740 (most recent call first): [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/zipfile.py", line 1194 in write [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/numpy/lib/_format_impl.py", line 777 in write_array [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/numpy/lib/_npyio_impl.py", line 786 in _savez [08:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/numpy/lib/_npyio_impl.py", line 753 in savez_compressed [08:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/node.py", line 271 in execute [08:51] [ComfyUI] File "/workspaces/DepthAnythingV3-0833/ComfyUI/comfy_api/latest/_io.py", line 1833 in EXECUTE_NORMALIZED [08:51] [ComfyUI] File "/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py", line 1762 in main [08:51] [ComfyUI] File "/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py", line 1807 in [08:51] [ComfyUI] [08:51] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] === END === [08:51] [ComfyUI] [08:53] [capture-loop] iter=1100 t=122.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=1 ram=8.4/31.3GB (27%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.97GB [08:59] [capture-loop] iter=1150 t=128.0s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=8.3/31.3GB (27%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.97GB [09:04] [capture-loop] iter=1200 t=133.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=8.3/31.3GB (27%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.97GB [09:10] [capture-loop] iter=1250 t=139.1s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=8.4/31.3GB (27%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=0.97GB [09:15] [capture-loop] iter=1300 t=144.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=6.7/31.3GB (22%) swap=0.0/32.0GB (0%) cpu=12% browser_rss=0.97GB [09:18] [ComfyUI] [SubprocessWorker] got response: ok [09:20] [ComfyUI] [comfy-env] Created 2 model patchers: ['DepthAnything3Net_1', 'VPRModel_2'] [09:20] [ComfyUI] [comfy-env] DepthAnythingV3_Streaming done (137.62s): result: NodeOutput [09:20] [ComfyUI] [VRAM] After DepthAnythingV3_Streaming: 2171 / 7703 MB [09:20] [ComfyUI] [VRAM] Loaded: SubprocessModel (335 MB), SubprocessModel (783 MB) [09:21] [capture-loop] iter=1350 t=150.1s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=1 ram=9.3/31.3GB (30%) swap=0.0/32.0GB (0%) cpu=18% browser_rss=0.98GB [09:22] [ComfyUI] Prompt executed in 150.86 seconds [09:22] Node executed (1 total), capturing... [09:22] Frame 22 saved (frame_021.jpg, t=151.2s) [09:22] [capture-node] freeze=2ms shot=135ms unfreeze=8ms saved=True [09:22] Execution complete (t=151.5s) [09:22] Captured 22 unique frames over 151.49s [09:22] [debug] iframes: 0 [09:22] [timing] trigger_3d_previews: 0.0s [09:25] Saved high-quality screenshot: da3_streaming_executed.png [09:25] [timing] final_screenshot: 0.2s [09:25] [ComfyUI] [comfy-env] [VRAM] Before offload 'VPRModel_2' (335 MB) -> cpu: 2171 / 7703 MB [09:25] Capturing execution frames: simple.json [09:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:25] [ComfyUI] [SubprocessWorker] call_id=31 sending model_to_device [09:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -318MB (now 811MB) reserved=1728MB peak=4556MB [09:25] [ComfyUI] [comfy-env] [VRAM] After offload 'VPRModel_2' (335 MB): 1339 / 7703 MB [09:25] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 1339 / 7703 MB [09:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:25] [ComfyUI] [SubprocessWorker] call_id=32 sending model_to_device [09:25] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 539 / 7703 MB [09:30] Frame 1 saved (frame_000.jpg, t=0.0s) [09:30] Validating workflow... [09:30] [ComfyUI] === /validate endpoint called === [09:30] [ComfyUI] Received JSON with keys: ['prompt'] [09:30] [ComfyUI] Prompt has 4 nodes [09:30] [ComfyUI] Node 2: LoadImage [09:30] [ComfyUI] Inputs: {"image": "bridge.jpg"} [09:30] Queuing workflow for execution... [09:30] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [09:30] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [09:30] [ComfyUI] Node 4: PreviewImage [09:30] [ComfyUI] Inputs: {"images": ["14", 0]} [09:30] [ComfyUI] Node 14: DepthAnything_V3 [09:30] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": true, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} [09:30] [ComfyUI] Generated prompt_id: f5b62989-2d7a-45a4-8bd6-59c53611b63e [09:30] [ComfyUI] Calling execution.validate_prompt()... [09:30] [ComfyUI] Validation result: valid=True [09:30] [ComfyUI] === Validation PASSED === [09:30] [ComfyUI] got prompt [09:30] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [09:30] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 539 / 7703 MB [09:30] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [09:30] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [09:30] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:30] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [09:30] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [09:30] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [09:30] [ComfyUI] [comfy-env] Invalidated 2 stale model patchers (will be cleaned up during next unload) [09:30] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-0833/ComfyUI', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [09:30] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [09:30] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py', 'abstract://comfy_worker_b25beceff74c']... [09:30] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_b25beceff74c (abstract, no filesystem path) [09:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [09:32] [ComfyUI] [SubprocessWorker] worker started/confirmed [09:32] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [09:32] [ComfyUI] [SubprocessWorker] created 0 shm blocks [09:32] [ComfyUI] [SubprocessWorker] sending request via socket... [09:32] [ComfyUI] [SubprocessWorker] call_id=33 sending call_method [09:32] [ComfyUI] [SubprocessWorker] got response: ok [09:32] [ComfyUI] [comfy-env] [VRAM] Before offload 'VPRModel_2' (335 MB) -> cpu: 269 / 7703 MB [09:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:32] [ComfyUI] [SubprocessWorker] call_id=34 sending model_to_device [09:32] [ComfyUI] Model 'VPRModel_2' gone from worker (restarted?), treating as offloaded [09:32] [ComfyUI] [comfy-env] [VRAM] After offload 'VPRModel_2' (335 MB): 269 / 7703 MB [09:32] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 269 / 7703 MB [09:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:32] [ComfyUI] [SubprocessWorker] call_id=35 sending model_to_device [09:32] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [09:32] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 269 / 7703 MB [09:32] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (1.62s): result: NodeOutput [09:32] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 269 / 7703 MB [09:32] [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 [09:32] [ComfyUI] [VRAM] Before DepthAnything_V3: 269 / 7703 MB [09:32] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [09:32] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [09:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:32] [ComfyUI] [SubprocessWorker] worker started/confirmed [09:32] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 683, 1024, 3]) [09:32] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [09:32] [ComfyUI] [SubprocessWorker] created 0 shm blocks [09:32] [ComfyUI] [SubprocessWorker] sending request via socket... [09:32] [ComfyUI] [SubprocessWorker] call_id=36 sending call_method [09:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [09:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 683, 1024, 3] [09:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 683, 1024, 3]) [09:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [09:33] Frame 2 saved (frame_001.jpg, t=2.3s) [09:33] [capture-periodic] freeze=2ms shot=135ms unfreeze=2ms saved=True [09:35] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=36 [09:35] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 7.80GB [09:35] [ComfyUI] [comfy-env] VRAM after eviction: 7.80GB [09:35] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +394MB (now 394MB) reserved=416MB peak=394MB [09:35] [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. [09:35] Frame 3 saved (frame_002.jpg, t=4.5s) [09:35] [capture-periodic] freeze=2ms shot=151ms unfreeze=2ms saved=True [09:36] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=36 [09:36] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +423MB (now 817MB) reserved=2560MB peak=1172MB [09:36] [capture-loop] iter=50 t=5.7s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=5 ram=5.1/31.3GB (16%) swap=0.0/32.0GB (0%) cpu=13% browser_rss=1.05GB [09:36] [ComfyUI] [SubprocessWorker] got response: ok [09:36] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [09:36] [ComfyUI] [comfy-env] DepthAnything_V3 done (3.92s): result: NodeOutput [09:36] [ComfyUI] [VRAM] After DepthAnything_V3: 2937 / 7703 MB [09:36] [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB) [09:36] [ComfyUI] Prompt executed in 5.59 seconds [09:36] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 2937 / 7703 MB [09:36] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:36] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:36] [ComfyUI] [SubprocessWorker] call_id=37 sending model_to_device [09:36] Node executed (1 total), capturing... [09:36] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 441 / 7703 MB [09:36] Frame 4 saved (frame_003.jpg, t=6.0s) [09:36] [capture-node] freeze=2ms shot=159ms unfreeze=0ms saved=True [09:36] Execution complete (t=6.0s) [09:36] Captured 4 unique frames over 6.26s [09:36] [debug] iframes: 0 [09:36] [timing] trigger_3d_previews: 0.0s [09:39] Saved high-quality screenshot: simple_executed.png [09:39] [timing] final_screenshot: 0.3s [09:39] Capturing execution frames: video_multiview_depth.json [09:44] Frame 1 saved (frame_000.jpg, t=0.0s) [09:44] Validating workflow... [09:44] [ComfyUI] === /validate endpoint called === [09:44] [ComfyUI] Received JSON with keys: ['prompt'] [09:44] [ComfyUI] Prompt has 9 nodes [09:44] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [09:44] [ComfyUI] Inputs: {"model": "da3_base.safetensors", "precision": "auto", "attention": "auto"} [09:44] [ComfyUI] Node 52: CreateVideo [09:44] Queuing workflow for execution... [09:44] [ComfyUI] Inputs: {"fps": 10, "images": ["62", 0]} [09:44] [ComfyUI] Node 53: CreateVideo [09:44] [ComfyUI] Inputs: {"fps": 10, "images": ["61", 0]} [09:44] [ComfyUI] Node 54: SaveVideo [09:44] [ComfyUI] Inputs: {"filename_prefix": "video/ComfyUI", "format": "auto", "codec": "auto", "video": ["52", 0]} [09:44] [ComfyUI] Node 55: SaveVideo [09:44] [ComfyUI] Inputs: {"filename_prefix": "video/ComfyUI", "format": "auto", "codec": "auto", "video": ["53", 0]} [09:44] [ComfyUI] Node 61: DepthAnything_V3 [09:44] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["71", 0]} [09:44] [ComfyUI] Node 62: DepthAnythingV3_MultiView [09:44] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["71", 0]} [09:44] [ComfyUI] Node 66: PreviewImage [09:44] [ComfyUI] Inputs: {"images": ["71", 0]} [09:44] [ComfyUI] Node 71: LoadImagesFromFolderKJ [09:44] [ComfyUI] Inputs: {"folder": "input/robotframes", "width": 1024, "height": 576, "keep_aspect_ratio": "crop", "image_load_cap": 0, "start_index": 0, "include_subfolders": false} [09:44] [ComfyUI] Generated prompt_id: 84c28758-55b2-4607-b612-85a896161556 [09:44] [ComfyUI] Calling execution.validate_prompt()... [09:44] [ComfyUI] Validation result: valid=True [09:44] [ComfyUI] === Validation PASSED === [09:44] [ComfyUI] got prompt [09:45] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_base.safetensors', precision: 'auto', attention: 'auto' [09:45] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [09:45] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-0833/ComfyUI', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages', '/workspaces/DepthAnythingV3-0833/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [09:45] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 441 / 7703 MB [09:45] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [09:45] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [09:45] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_u36y2nop/persistent_worker.py', 'abstract://comfy_worker_e6e05c72cf5e']... [09:45] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_e6e05c72cf5e (abstract, no filesystem path) [09:45] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [09:45] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:45] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [09:45] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [09:45] [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload) [09:45] Node executed (1 total), capturing... [09:46] Frame 2 saved (frame_001.jpg, t=1.3s) [09:46] [capture-node] freeze=2ms shot=137ms unfreeze=5ms saved=True [09:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [09:47] [ComfyUI] [SubprocessWorker] worker started/confirmed [09:47] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [09:47] [ComfyUI] [SubprocessWorker] created 0 shm blocks [09:47] [ComfyUI] [SubprocessWorker] sending request via socket... [09:47] [ComfyUI] [SubprocessWorker] call_id=38 sending call_method [09:47] [ComfyUI] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. [09:47] [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. [09:47] [ComfyUI] [09:50] Frame 3 saved (frame_002.jpg, t=5.8s) [09:50] [capture-periodic] freeze=2ms shot=154ms unfreeze=3ms saved=True [09:50] [capture-loop] iter=50 t=6.1s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=2 ram=4.3/31.3GB (14%) swap=0.0/32.0GB (0%) cpu=10% browser_rss=1.18GB [09:51] [ComfyUI] model.safetensors: 0%| | 0.00/542M [00:00 cpu: 269 / 7703 MB [09:55] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:55] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:55] [ComfyUI] [SubprocessWorker] call_id=39 sending model_to_device [09:55] [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded [09:55] [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 269 / 7703 MB [09:55] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (9.71s): result: NodeOutput [09:55] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 269 / 7703 MB [09:55] [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 [09:55] [ComfyUI] [VRAM] Before DepthAnything_V3: 269 / 7703 MB [09:55] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [09:55] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [09:55] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:55] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:55] [ComfyUI] [SubprocessWorker] worker started/confirmed [09:55] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([13, 576, 1024, 3]) [09:55] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [09:55] [ComfyUI] [SubprocessWorker] created 0 shm blocks [09:55] [ComfyUI] [SubprocessWorker] sending request via socket... [09:55] [ComfyUI] [SubprocessWorker] call_id=40 sending call_method [09:55] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [09:55] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[13, 576, 1024, 3] [09:55] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([13, 576, 1024, 3]) [09:55] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [09:56] [capture-loop] iter=100 t=11.6s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=1 ram=4.2/31.3GB (13%) swap=0.0/32.0GB (0%) cpu=11% browser_rss=1.03GB [09:57] Frame 5 saved (frame_004.jpg, t=12.5s) [09:57] [capture-periodic] freeze=1ms shot=114ms unfreeze=2ms saved=True [09:57] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=40 [09:57] [ComfyUI] [comfy-env] VRAM request: 0.27GB, free before eviction: 7.80GB [09:57] [ComfyUI] [comfy-env] VRAM after eviction: 7.80GB [09:57] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +258MB (now 258MB) reserved=288MB peak=258MB [09:57] [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. [09:58] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:58] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:58] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +210MB (now 469MB) reserved=640MB peak=810MB [09:58] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:58] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:59] Frame 6 saved (frame_005.jpg, t=14.8s) [09:59] [capture-periodic] freeze=1ms shot=118ms unfreeze=2ms saved=True [09:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [09:59] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=40 [10:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -202MB (now 267MB) reserved=1120MB peak=810MB [10:01] [ComfyUI] [SubprocessWorker] got response: ok [10:01] [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1'] [10:01] [ComfyUI] [comfy-env] DepthAnything_V3 done (5.92s): result: NodeOutput [10:01] [ComfyUI] [VRAM] After DepthAnything_V3: 1497 / 7703 MB [10:01] [ComfyUI] [VRAM] Loaded: SubprocessModel (258 MB) [10:01] [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 [10:01] [ComfyUI] [VRAM] Before DepthAnythingV3_MultiView: 1497 / 7703 MB [10:01] [ComfyUI] [VRAM] Loaded: SubprocessModel (258 MB) [10:01] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [10:01] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [10:01] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [10:01] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [10:01] [ComfyUI] [SubprocessWorker] worker started/confirmed [10:01] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([13, 576, 1024, 3]) [10:01] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [10:01] [ComfyUI] [SubprocessWorker] created 0 shm blocks [10:01] [ComfyUI] [SubprocessWorker] sending request via socket... [10:01] [ComfyUI] [SubprocessWorker] call_id=41 sending call_method [10:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [10:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[13, 576, 1024, 3] [10:01] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([13, 576, 1024, 3]) [10:01] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=41 [10:01] [ComfyUI] [comfy-env] VRAM request: 0.27GB, free before eviction: 6.51GB [10:01] [ComfyUI] [comfy-env] VRAM after eviction: 6.51GB [10:01] [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. [10:01] Node executed (2 total), capturing... [10:02] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +443MB (now 711MB) reserved=1088MB peak=810MB [10:02] Frame 7 saved (frame_006.jpg, t=17.2s) [10:02] [capture-node] freeze=2ms shot=136ms unfreeze=1ms saved=True [10:02] [capture-loop] iter=150 t=17.4s state={'complete': False, 'error': None, 'executedCount': 2, 'wsState': 1} eval_ms=2 ram=6.2/31.3GB (20%) swap=0.0/32.0GB (0%) cpu=15% browser_rss=1.11GB [10:03] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +705MB (now 1416MB) reserved=1888MB peak=1416MB [10:04] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -764MB (now 653MB) reserved=2720MB peak=1458MB [10:04] Frame 8 saved (frame_007.jpg, t=19.4s) [10:04] [capture-periodic] freeze=2ms shot=135ms unfreeze=5ms saved=True [10:05] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -387MB (now 267MB) reserved=2720MB peak=1458MB [10:05] [ComfyUI] [SubprocessWorker] got response: ok [10:05] [ComfyUI] [comfy-env] DepthAnythingV3_MultiView done (3.53s): result: NodeOutput [10:05] [ComfyUI] [VRAM] After DepthAnythingV3_MultiView: 3097 / 7703 MB [10:05] [ComfyUI] [VRAM] Loaded: SubprocessModel (258 MB) [10:05] [ComfyUI] Prompt executed in 20.43 seconds [10:05] Node executed (3 total), capturing... [10:05] Frame 9 saved (frame_008.jpg, t=20.8s) [10:05] [capture-node] freeze=2ms shot=118ms unfreeze=8ms saved=True [10:05] Execution complete (t=21.1s) [10:05] Captured 9 unique frames over 21.06s [10:05] [debug] iframes: 0 [10:05] [timing] trigger_3d_previews: 0.0s [10:08] Saved high-quality screenshot: video_multiview_depth_executed.png [10:08] [timing] final_screenshot: 0.3s [10:08] [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (258 MB) -> cpu: 3097 / 7703 MB [10:08] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [10:08] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [10:08] [ComfyUI] [SubprocessWorker] call_id=42 sending model_to_device [10:08] Results saved to /logs/DepthAnythingV3-0833/dev/linux-gpu/results.json [10:08] Model report: 9 files, 2.4 GB -> /logs/DepthAnythingV3-0833/dev/linux-gpu/models.json [10:08] Saved: /logs/DepthAnythingV3-0833/dev/linux-gpu/index.html [10:08] [EXECUTION] PASSED [10:08] linux: PASSED [10:08] Stopping ComfyUI server...