[00:00] Crash dump logging enabled: /logs/DepthAnythingV3-1231/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/DepthAnythingV3-1231/.venv --python 3.11 [00:00] Cloning ComfyUI (latest)... [00:00] Running: git clone --depth 1 https://github.com/comfyanonymous/ComfyUI.git /workspaces/DepthAnythingV3-1231/ComfyUI [00:02] Installing ComfyUI requirements... [00:02] Running: uv pip install --python /workspaces/DepthAnythingV3-1231/.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/DepthAnythingV3-1231/ComfyUI/requirements.txt [02:12] Installing custom node... [02:12] Copying ComfyUI-DepthAnythingV3 to custom_nodes/... [02:12] Installing node requirements... [02:12] Running: uv pip install --python /workspaces/DepthAnythingV3-1231/.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/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/requirements.txt [02:14] Running install.py... [02:14] Running: /workspaces/DepthAnythingV3-1231/.venv/bin/python /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/install.py [02:15] [02:15] Installing 3 node dependencies... [02:15] Cloning ComfyUI-VideoHelperSuite... [02:16] Installing requirements for ComfyUI-VideoHelperSuite... [02:18] Cloning ComfyUI-KJNodes... [02:21] Installing requirements for ComfyUI-KJNodes... [02:22] Cloning ComfyUI-GeometryPack... [02:27] Installing requirements for ComfyUI-GeometryPack... [02:28] Running install.py for ComfyUI-GeometryPack... [02:30] [comfy-env] _discover: scanning /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes [02:30] [comfy-env] _discover: ComfyUI-DepthAnythingV3 -> depthanythingv3-nodes (custom_nodes/ComfyUI-DepthAnythingV3/nodes/comfy-env.toml) [02:30] [comfy-env] _discover: ComfyUI-GeometryPack -> geometrypack-nodes (custom_nodes/ComfyUI-GeometryPack/nodes/comfy-env.toml) [02:30] [comfy-env] _discover: ComfyUI-KJNodes: no comfy-env.toml found [02:30] [comfy-env] _discover: ComfyUI-VideoHelperSuite: no comfy-env.toml found [02:30] [comfy-env] Workspace: /root/.ce [02:30] [comfy-env] ComfyUI: /workspaces/DepthAnythingV3-1231/ComfyUI [02:30] [comfy-env] Found 2 node config(s): [02:30] - depthanythingv3-nodes <- custom_nodes/ComfyUI-DepthAnythingV3/nodes/comfy-env.toml (python=host) [02:30] - geometrypack-nodes <- custom_nodes/ComfyUI-GeometryPack/nodes/comfy-env.toml (python=host) [02:30] [comfy-env] Bootstrap interpreter has python 3.11 + torch 2.11.0 (cu128). Looking for cuda-only wheels matching cu128/torch2.11/cp311. [02:30] [comfy-env] GPU: Detection: smi [02:30] Driver: 580.126.20 [02:30] CUDA: 13.0 [02:30] Recommended: CUDA 13.0 [02:30] [02:30] GPU 0: NVIDIA GeForce RTX 3090 (sm_86) [Ampere] 24576MB [02:30] [comfy-env] Comfyui feature -> torch 2.11.0 from https://download.pytorch.org/whl/cu128 (CUDA 12.8 via bootstrap torch) [02:30] [comfy-env] cuda-wheels: 3 package(s) need a matched (cuda, torch, python) combo: ['flash_attn', 'sageattention', 'cumesh'] [02:30] [comfy-env] cuda-wheels tier 1 (bootstrap): probing cu12.8/torch2.11/cp311 [02:30] [cuda-wheels] Looking up flash_attn: cu128 torch2.11 cp311 manylinux linux [02:31] [cuda-wheels] Found: flash_attn-2.8.3+cu128torch2.11-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [02:31] [cuda-wheels] Looking up sageattention: cu128 torch2.11 cp311 manylinux linux [02:31] [cuda-wheels] Found: sageattention-2.2.0+cu128torch2.11-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [02:31] [cuda-wheels] Looking up cumesh: cu128 torch2.11 cp311 manylinux linux [02:31] [cuda-wheels] Found: cumesh-0.0.1+cu128torch2.11-cp311-cp311-manylinux_2_35_x86_64.whl [02:31] [comfy-env] cuda-wheels combo: cu12.8/torch2.11 (bootstrap matches; per-node envs will pin to this) [02:31] [comfy-env] Host glibc 2.35 -> system-requirements [02:31] [cuda-wheels] Looking up flash_attn: cu128 torch2.11 cp311 manylinux linux [02:31] [cuda-wheels] Found: flash_attn-2.8.3+cu128torch2.11-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [02:31] [cuda-wheels] Looking up sageattention: cu128 torch2.11 cp311 manylinux linux [02:31] [cuda-wheels] Found: sageattention-2.2.0+cu128torch2.11-cp311-cp311-manylinux_2_34_x86_64.manylinux_2_35_x86_64.whl [02:31] [comfy-env] depthanythingv3-nodes: cuda-wheels deferred for post-pixi install (flash_attn, sageattention) [02:31] [cuda-wheels] Looking up cumesh: cu128 torch2.11 cp311 manylinux linux [02:31] [cuda-wheels] Found: cumesh-0.0.1+cu128torch2.11-cp311-cp311-manylinux_2_35_x86_64.whl [02:31] [comfy-env] geometrypack-nodes: cuda-wheels deferred for post-pixi install (cumesh) [02:31] Generated /root/.ce/pixi.toml [02:31] [comfy-env] Installing 2 environment(s): [02:31] - depthanythingv3-nodes (python=host, 11 pypi deps, 2 cuda wheels) [02:31] - geometrypack-nodes (python=host, 14 pypi deps, 1 cuda wheels) [02:31] [comfy-env] Running `pixi install -e depthanythingv3-nodes -e geometrypack-nodes`... [02:39] WARN Skipped running the post-link scripts because `run-post-link-scripts` = `false` [02:39] - bin/.librsvg-pre-unlink.sh [02:39] To enable them, run: [02:39] pixi config set --local run-post-link-scripts insecure [02:39] More info: [02:39] https://pixi.sh/latest/reference/pixi_configuration/#run-post-link-scripts [02:58] WARN Skipped running the post-link scripts because `run-post-link-scripts` = `false` [02:58] - bin/.librsvg-pre-unlink.sh [02:58] To enable them, run: [02:58] pixi config set --local run-post-link-scripts insecure [02:58] More info: [02:58] https://pixi.sh/latest/reference/pixi_configuration/#run-post-link-scripts [04:44] The following environments have been installed: depthanythingv3-nodes, geometrypack-nodes. [04:44] [comfy-env] depthanythingv3-nodes: installing cuda-wheels with --no-deps (flash_attn, sageattention) [04:45] Using Python 3.11.15 environment at: .pixi/envs/depthanythingv3-nodes [04:47] Resolved 2 packages in 2.18s [04:47] Downloading flash-attn (242.3MiB) [04:47] Downloading sageattention (53.2MiB) [04:49] Downloaded sageattention [04:54] Downloaded flash-attn [04:54] Prepared 2 packages in 7.40s [04:54] Installed 2 packages in 9ms [04:54] + 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) [04:54] + 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) [04:54] [comfy-env] geometrypack-nodes: installing cuda-wheels with --no-deps (cumesh) [04:54] Using Python 3.11.15 environment at: .pixi/envs/geometrypack-nodes [04:55] Resolved 1 package in 931ms [04:55] Downloading cumesh (19.5MiB) [04:56] Downloaded cumesh [04:56] Prepared 1 package in 462ms [04:56] Installed 1 package in 6ms [04:56] + 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) [04:56] [comfy-env] Recorded install hash 2fe352e17cb2 -> /root/.ce/install.hash [04:56] [comfy-env] Install log: /root/.ce/install.log [04:56] [04:56] Installation complete! [04:56] [04:56] [requirements] Re-installing main package requirements... [04:56] Installing requirements for ComfyUI-DepthAnythingV3... [04:56] [comfy-env] _discover: scanning /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes [04:56] [comfy-env] _discover: ComfyUI-DepthAnythingV3 -> depthanythingv3-nodes (custom_nodes/ComfyUI-DepthAnythingV3/nodes/comfy-env.toml) [04:56] [comfy-env] _discover: ComfyUI-GeometryPack -> geometrypack-nodes (custom_nodes/ComfyUI-GeometryPack/nodes/comfy-env.toml) [04:56] [comfy-env] _discover: ComfyUI-KJNodes: no comfy-env.toml found [04:56] [comfy-env] _discover: ComfyUI-VideoHelperSuite: no comfy-env.toml found [04:56] [comfy-env] Workspace inputs unchanged (hash 2fe352e17cb2) -- skipping install. Delete /root/.ce/install.hash to force. [04:56] [04:56] Installation complete! [04:56] Installing 3 node dependency(ies)... [04:56] ComfyUI-VideoHelperSuite from Kosinkadink/ComfyUI-VideoHelperSuite [04:56] ComfyUI-VideoHelperSuite already exists, skipping... [04:56] ComfyUI-KJNodes from kijai/ComfyUI-KJNodes [04:56] ComfyUI-KJNodes already exists, skipping... [04:56] ComfyUI-GeometryPack from PozzettiAndrea/ComfyUI-GeometryPack [04:56] ComfyUI-GeometryPack already exists, skipping... [04:56] Installing validation endpoint... [04:56] Cloning PozzettiAndrea/ComfyUI-validate-endpoint... [04:56] Running: git clone --depth 1 https://github.com/PozzettiAndrea/ComfyUI-validate-endpoint.git /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-validate-endpoint [04:57] CUDA packages absent (will mock): flash_attn, sageattention [04:57] [INSTALL] PASSED [04:57] [04:57] [3/5] REGISTRATION [04:57] ---------------------------------------- [04:57] [DEBUG] server=None, server_url=None, api=None [04:57] Starting ComfyUI server... [04:57] Starting ComfyUI server on port 41884... [04:57] CUDA mock packages: flash_attn, sageattention [04:57] Starting ComfyUI server on port 41884... [04:57] Waiting for server to be ready (timeout: 600s)... [04:58] [ComfyUI] setup plugin alembic.autogenerate.schemas [04:58] [ComfyUI] setup plugin alembic.autogenerate.tables [04:58] [ComfyUI] setup plugin alembic.autogenerate.types [04:58] [ComfyUI] setup plugin alembic.autogenerate.constraints [04:58] [ComfyUI] setup plugin alembic.autogenerate.defaults [04:58] [ComfyUI] setup plugin alembic.autogenerate.comments [04:59] [ComfyUI] [comfy-env] ComfyUI-DepthAnythingV3: 1 isolation env(s): [04:59] [ComfyUI] [comfy-env] nodes -> /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes [04:59] [ComfyUI] [comfy-env] Workspace: /root/.ce [04:59] [ComfyUI] [comfy-env] env: /root/.ce/.pixi/envs/depthanythingv3-nodes [OK] [04:59] [ComfyUI] [comfy-env] prestartup complete [04:59] [ComfyUI] [comfy-env] ComfyUI-GeometryPack: 1 isolation env(s): [04:59] [ComfyUI] [comfy-env] nodes -> /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-GeometryPack/nodes [04:59] [ComfyUI] [comfy-env] env: /root/.ce/.pixi/envs/geometrypack-nodes [OK] [04:59] [ComfyUI] [comfy-env] prestartup complete [04:59] [ComfyUI] [04:59] [ComfyUI] Prestartup times for custom nodes: [04:59] [ComfyUI] 0.1 seconds: /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-GeometryPack [04:59] [ComfyUI] 0.3 seconds: /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 [04:59] [ComfyUI] [05:07] [ComfyUI] WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations. [05:07] [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']} [05:07] [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']} [05:07] [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']} [05:07] [ComfyUI] Checkpoint files will always be loaded safely. [05:07] [ComfyUI] Total VRAM 24124 MB, total RAM 31924 MB [05:07] [ComfyUI] pytorch version: 2.11.0+cu128 [05:07] [ComfyUI] Set vram state to: NORMAL_VRAM [05:07] [ComfyUI] Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync [05:07] [ComfyUI] Using async weight offloading with 2 streams [05:07] [ComfyUI] Enabled pinned memory 28731.0 [05:07] [ComfyUI] Using pytorch attention [05:14] [ComfyUI] aimdo: /project/src-posix/cuda-funchooks.c:52:DEBUG:aimdo_setup_hooks: hooks successfully installed [05:14] [ComfyUI] aimdo: /project/src/control.c:151:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 3090 (VRAM: 24124 MB) [05:14] [ComfyUI] DynamicVRAM support detected and enabled [05:14] [ComfyUI] Python version: 3.11.15 (main, May 8 2026, 18:33:10) [Clang 22.1.3 ] [05:14] [ComfyUI] ComfyUI version: 0.21.0 [05:14] [ComfyUI] comfy-aimdo version: 0.3.0 [05:14] [ComfyUI] comfy-kitchen version: 0.2.8 [05:14] [ComfyUI] ****** User settings have been changed to be stored on the server instead of browser storage. ****** [05:14] [ComfyUI] ****** For multi-user setups add the --multi-user CLI argument to enable multiple user profiles. ****** [05:14] [ComfyUI] ComfyUI frontend version: 1.43.18 [05:14] [ComfyUI] [Prompt Server] web root: /workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfyui_frontend_package/static [05:14] [ComfyUI] Asset seeder disabled [05:17] [ComfyUI] [comfy-env] Version: 0.3.87 [05:17] [ComfyUI] [comfy-env] register_nodes: ComfyUI-DepthAnythingV3 [05:17] [ComfyUI] [comfy-env] ComfyUI source dir: /workspaces/DepthAnythingV3-1231/ComfyUI [05:17] [ComfyUI] [comfy-env] Found 1 isolation env(s) [05:17] [ComfyUI] [comfy-env] Scanning nodes metadata (isolation root)... [05:17] [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_1peurvmn.py /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 nodes /tmp/comfy_meta_out_ojkaq2ui.pkl [05:17] [ComfyUI] [comfy-env] Scan env PATH for nodes: [05:17] [ComfyUI] [comfy-env] [0] /root/.local/bin [05:17] [ComfyUI] [comfy-env] [1] /usr/local/nvidia/bin [05:17] [ComfyUI] [comfy-env] [2] /usr/local/cuda/bin [05:17] [ComfyUI] [comfy-env] [3] /usr/local/sbin [05:17] [ComfyUI] [comfy-env] [4] /usr/local/bin [05:17] [ComfyUI] [comfy-env] [5] /usr/sbin [05:17] [ComfyUI] [comfy-env] [6] /usr/bin [05:17] [ComfyUI] [comfy-env] [7] /sbin [05:17] [ComfyUI] [comfy-env] [8] /bin [05:22] [ComfyUI] [comfy-env] Metadata scan stderr for nodes: [05:22] [ComfyUI] [comfy-env] [meta-scan] importing nodes from /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 [05:22] [ComfyUI] [comfy-env] ERROR:root:Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [05:22] [ComfyUI] [comfy-env] [meta-scan] import OK [05:22] [ComfyUI] [comfy-env] Scanned nodes: 15 nodes (4.7s) [05:22] [ComfyUI] [comfy-env] Scanned nodes root: 15 nodes (4.7s) [05:22] [ComfyUI] [comfy-env] Imported nodes root: 15 nodes (isolation) [05:22] [ComfyUI] [comfy-env] Registered 15 total nodes [05:22] [ComfyUI] loading... [05:22] [ComfyUI] calling register_nodes [05:22] [ComfyUI] [comfy-env] Version: 0.3.87 [05:22] [ComfyUI] [comfy-env] register_nodes: ComfyUI-GeometryPack [05:22] [ComfyUI] [comfy-env] ComfyUI source dir: /workspaces/DepthAnythingV3-1231/ComfyUI [05:22] [ComfyUI] [comfy-env] Found 1 isolation env(s) [05:22] [ComfyUI] [comfy-env] Scanning nodes metadata (isolation root)... [05:22] [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_3wg92mek.py /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-GeometryPack nodes /tmp/comfy_meta_out_q_bu8zrv.pkl [05:22] [ComfyUI] [comfy-env] Scan env PATH for nodes: [05:22] [ComfyUI] [comfy-env] [0] /root/.local/bin [05:22] [ComfyUI] [comfy-env] [1] /usr/local/nvidia/bin [05:22] [ComfyUI] [comfy-env] [2] /usr/local/cuda/bin [05:22] [ComfyUI] [comfy-env] [3] /usr/local/sbin [05:22] [ComfyUI] [comfy-env] [4] /usr/local/bin [05:22] [ComfyUI] [comfy-env] [5] /usr/sbin [05:22] [ComfyUI] [comfy-env] [6] /usr/bin [05:22] [ComfyUI] [comfy-env] [7] /sbin [05:22] [ComfyUI] [comfy-env] [8] /bin [05:29] [ComfyUI] [comfy-env] Metadata scan stderr for nodes: [05:29] [ComfyUI] [comfy-env] [meta-scan] importing nodes from /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-GeometryPack [05:29] [ComfyUI] [comfy-env] ERROR:root:Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [05:29] [ComfyUI] [comfy-env] [meta-scan] import OK [05:29] [ComfyUI] [comfy-env] Scanned nodes: 125 nodes (7.7s) [05:29] [ComfyUI] [comfy-env] Scanned nodes root: 125 nodes (7.7s) [05:29] [ComfyUI] [comfy-env] Imported nodes root: 125 nodes (isolation) [05:29] [ComfyUI] [comfy-env] Registered 125 total nodes [05:30] [ComfyUI] [05:30] [ComfyUI] Import times for custom nodes: [05:30] [ComfyUI] 0.0 seconds: /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/websocket_image_save.py [05:30] [ComfyUI] 0.0 seconds: /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-validate-endpoint [05:30] [ComfyUI] 0.1 seconds: /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite [05:30] [ComfyUI] 0.2 seconds: /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-KJNodes [05:30] [ComfyUI] 4.9 seconds: /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3 [05:30] [ComfyUI] 7.8 seconds: /workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-GeometryPack [05:30] [ComfyUI] [05:30] [ComfyUI] Context impl SQLiteImpl. [05:30] [ComfyUI] Will assume non-transactional DDL. [05:30] [ComfyUI] Context impl SQLiteImpl. [05:30] [ComfyUI] Will assume non-transactional DDL. [05:30] [ComfyUI] Running upgrade -> 0001_assets, Initial assets schema [05:30] [ComfyUI] Revision ID: 0001_assets [05:30] [ComfyUI] Revises: None [05:30] [ComfyUI] Create Date: 2025-12-10 00:00:00 [05:30] [ComfyUI] Running upgrade 0001_assets -> 0002_merge_to_asset_references, Merge AssetInfo and AssetCacheState into unified asset_references table. [05:30] [ComfyUI] Running upgrade 0002_merge_to_asset_references -> 0003_add_metadata_job_id, Add system_metadata and job_id columns to asset_references. [05:30] [ComfyUI] Change preview_id FK from assets.id to asset_references.id. [05:30] [ComfyUI] Database upgraded from None to 0003_add_metadata_job_id [05:30] [ComfyUI] Starting server [05:30] [ComfyUI] [05:30] [ComfyUI] To see the GUI go to: http://127.0.0.1:41884 [05:31] Server responding, waiting for nodes to load... [05:51] Server is ready! [05:51] Checking for import errors in server logs... [05:51] No import errors detected [05:51] Found 1129 registered nodes [05:51] [REGISTRATION] PASSED [05:51] [05:51] [4/5] INSTANTIATION [05:51] ---------------------------------------- [05:51] [DEBUG] server=, server_url=None, api= [05:51] Testing node constructors... [05:51] All 15 node(s) instantiated successfully! [05:51] [INSTANTIATION] PASSED [05:51] [05:51] [5/5] EXECUTION [05:51] ---------------------------------------- [05:51] [DEBUG] server=, server_url=None, api= [05:51] GPU runner - will execute 7 workflow(s) [05:51] Running 7 workflow(s) (all with videos)... [05:51] Installing screenshot dependencies (playwright, pillow)... [05:53] Packages installed, downloading chromium browser... [06:15] Screenshot dependencies installed successfully [06:16] Starting headless browser... [06:16] Installing Vulkan stack (apt)... [06:16] Vulkan install error: [Errno 2] No such file or directory: 'sudo' [06:16] GPU detected (no Vulkan) -- using ANGLE/OpenGL rendering [06:16] Capturing execution frames: advanced.json [06:19] [ComfyUI] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version. [06:25] Frame 1 saved (frame_000.jpg, t=0.0s) [06:25] Validating workflow... [06:25] [ComfyUI] === /validate endpoint called === [06:25] [ComfyUI] Received JSON with keys: ['prompt'] [06:25] [ComfyUI] Prompt has 11 nodes [06:25] [ComfyUI] Node 2: LoadImage [06:25] Queuing workflow for execution... [06:25] [ComfyUI] Inputs: {"image": "bridge.jpg"} [06:25] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [06:25] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [06:25] [ComfyUI] Node 4: PreviewImage [06:25] [ComfyUI] Inputs: {"images": ["12", 0]} [06:25] [ComfyUI] Node 6: PreviewImage [06:25] [ComfyUI] Inputs: {"images": ["12", 1]} [06:25] [ComfyUI] Node 7: PreviewImage [06:25] [ComfyUI] Inputs: {"images": ["12", 2]} [06:25] [ComfyUI] Node 8: PreviewImage [06:25] [ComfyUI] Inputs: {"images": ["12", 3]} [06:25] [ComfyUI] Node 9: PreviewAny [06:25] [ComfyUI] Inputs: {"source": ["12", 6]} [06:25] [ComfyUI] Node 10: PreviewAny [06:25] [ComfyUI] Inputs: {"source": ["12", 5]} [06:25] [ComfyUI] Node 11: MaskPreview [06:25] [ComfyUI] Inputs: {"mask": ["12", 7]} [06:25] [ComfyUI] Node 12: DepthAnything_V3 [06:25] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} [06:25] [ComfyUI] Node 13: PreviewImage [06:25] [ComfyUI] Inputs: {"images": ["12", 4]} [06:25] [ComfyUI] Generated prompt_id: ea74b14a-1d8f-46b5-998f-c0877e565cbc [06:25] [ComfyUI] Calling execution.validate_prompt()... [06:25] [ComfyUI] Validation result: valid=True [06:25] [ComfyUI] === Validation PASSED === [06:25] [ComfyUI] got prompt [06:25] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [06:25] [ComfyUI] [comfy-env] SubprocessWorker: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:25] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 22353 / 24124 MB [06:25] [ComfyUI] [comfy-env] env_vars: {'COMFYUI_BASE': '/workspaces/DepthAnythingV3-1231/ComfyUI'} [06:25] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [06:25] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:25] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [06:25] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1231/ComfyUI', '/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.1/site-packages', '/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [06:25] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [06:25] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py', 'abstract://comfy_worker_dbc1c1ce7155']... [06:25] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_dbc1c1ce7155 (abstract, no filesystem path) [06:27] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [06:27] Frame 2 saved (frame_001.jpg, t=2.5s) [06:27] [capture-periodic] freeze=4ms shot=210ms unfreeze=5ms saved=True [06:27] [ComfyUI] [SubprocessWorker] worker started/confirmed [06:27] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [06:27] [ComfyUI] [SubprocessWorker] created 0 shm blocks [06:27] [ComfyUI] [SubprocessWorker] sending request via socket... [06:27] [ComfyUI] [SubprocessWorker] call_id=1 sending call_method [06:28] [ComfyUI] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. [06:28] [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. [06:28] [ComfyUI] [06:29] Frame 3 saved (frame_002.jpg, t=4.9s) [06:29] [capture-periodic] freeze=4ms shot=198ms unfreeze=11ms saved=True [06:31] [capture-loop] iter=50 t=6.3s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=24.8/31.2GB (80%) swap=19.8/32.0GB (62%) cpu=6% browser_rss=0.85GB [06:32] [ComfyUI] model.safetensors: 0%| | 0.00/1.64G [00:00 [07:25] [ComfyUI] [07:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] === END === [07:25] [ComfyUI] [07:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +267MB (now 267MB) reserved=288MB peak=267MB [07:25] [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. [07:29] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +324MB (now 591MB) reserved=736MB peak=591MB [07:29] [ComfyUI] [SubprocessWorker] got response: error [07:29] [ComfyUI] !!! Exception during processing !!! Allocation on device 0 would exceed allowed memory. (out of memory) [07:29] [ComfyUI] Currently allocated : 936.80 MiB [07:29] [ComfyUI] Requested : 223.56 MiB [07:29] [ComfyUI] Device limit : 23.56 GiB [07:29] [ComfyUI] Free (according to CUDA): 18.25 MiB [07:29] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [07:29] [ComfyUI] : 17179869184.00 GiB [07:29] [ComfyUI] [07:29] [ComfyUI] Worker traceback: [07:29] [ComfyUI] Traceback (most recent call last): [07:29] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [07:29] [ComfyUI] result = method(**inputs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [07:29] [ComfyUI] to_return = cls.execute(*args, **kwargs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute [07:29] [ComfyUI] output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [07:29] [ComfyUI] return self._call_impl(*args, **kwargs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [07:29] [ComfyUI] return forward_call(*args, **kwargs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [07:29] [ComfyUI] output = self._process_depth_head(feats, H, W) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [07:29] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [07:29] [ComfyUI] return self._call_impl(*args, **kwargs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [07:29] [ComfyUI] return forward_call(*args, **kwargs) [07:29] [capture-loop] iter=550 t=65.1s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=24.0/31.2GB (77%) swap=21.6/32.0GB (67%) cpu=5% browser_rss=0.78GB [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward [07:29] [ComfyUI] out_dict = self._forward_impl(feats, H, W, patch_start_idx) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl [07:29] [ComfyUI] fused_main, fused_aux_pyr = self._fuse(resized_feats) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse [07:29] [ComfyUI] out = self.scratch.refinenet1(out, l1_rn) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [07:29] [ComfyUI] return self._call_impl(*args, **kwargs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [07:29] [ComfyUI] return forward_call(*args, **kwargs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward [07:29] [ComfyUI] y = self.out_conv(y) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [07:29] [ComfyUI] return self._call_impl(*args, **kwargs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [07:29] [ComfyUI] return forward_call(*args, **kwargs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward [07:29] [ComfyUI] return self.forward_comfy_cast_weights(*args, **kwargs) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights [07:29] [ComfyUI] x = self._conv_forward(input, weight, bias) [07:29] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:29] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward [07:29] [ComfyUI] return F.conv2d( [07:29] [ComfyUI] ^^^^^^^^^ [07:29] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [07:29] [ComfyUI] Currently allocated : 936.80 MiB [07:29] [ComfyUI] Requested : 223.56 MiB [07:29] [ComfyUI] Device limit : 23.56 GiB [07:29] [ComfyUI] Free (according to CUDA): 18.25 MiB [07:29] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [07:29] [ComfyUI] : 17179869184.00 GiB [07:29] [ComfyUI] [07:29] [ComfyUI] Traceback (most recent call last): [07:29] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute [07:30] [ComfyUI] output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data [07:30] [ComfyUI] return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list [07:30] [ComfyUI] await process_inputs(input_dict, i) [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs [07:30] [ComfyUI] result = f(**inputs) [07:30] [ComfyUI] ^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy [07:30] [ComfyUI] result = worker.call_method( [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method [07:30] [ComfyUI] raise WorkerError( [07:30] [ComfyUI] comfy_env.isolation.workers.base.WorkerError: Allocation on device 0 would exceed allowed memory. (out of memory) [07:30] [ComfyUI] Currently allocated : 936.80 MiB [07:30] [ComfyUI] Requested : 223.56 MiB [07:30] [ComfyUI] Device limit : 23.56 GiB [07:30] [ComfyUI] Free (according to CUDA): 18.25 MiB [07:30] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [07:30] [ComfyUI] : 17179869184.00 GiB [07:30] [ComfyUI] [07:30] [ComfyUI] Worker traceback: [07:30] [ComfyUI] Traceback (most recent call last): [07:30] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [07:30] [ComfyUI] result = method(**inputs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [07:30] [ComfyUI] to_return = cls.execute(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute [07:30] [ComfyUI] output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [07:30] [ComfyUI] return self._call_impl(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [07:30] [ComfyUI] return forward_call(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [07:30] [ComfyUI] output = self._process_depth_head(feats, H, W) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [07:30] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [07:30] [ComfyUI] return self._call_impl(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [07:30] [ComfyUI] return forward_call(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward [07:30] [ComfyUI] out_dict = self._forward_impl(feats, H, W, patch_start_idx) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl [07:30] [ComfyUI] fused_main, fused_aux_pyr = self._fuse(resized_feats) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse [07:30] [ComfyUI] out = self.scratch.refinenet1(out, l1_rn) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [07:30] [ComfyUI] return self._call_impl(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [07:30] [ComfyUI] return forward_call(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward [07:30] [ComfyUI] y = self.out_conv(y) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [07:30] [ComfyUI] return self._call_impl(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [07:30] [ComfyUI] return forward_call(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward [07:30] [ComfyUI] return self.forward_comfy_cast_weights(*args, **kwargs) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights [07:30] [ComfyUI] x = self._conv_forward(input, weight, bias) [07:30] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [07:30] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward [07:30] [ComfyUI] return F.conv2d( [07:30] [ComfyUI] ^^^^^^^^^ [07:30] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [07:30] [ComfyUI] Currently allocated : 936.80 MiB [07:30] [ComfyUI] Requested : 223.56 MiB [07:30] [ComfyUI] Device limit : 23.56 GiB [07:30] [ComfyUI] Free (according to CUDA): 18.25 MiB [07:30] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [07:30] [ComfyUI] : 17179869184.00 GiB [07:30] [ComfyUI] [07:30] [ComfyUI] [07:30] [ComfyUI] Prompt executed in 64.60 seconds [07:30] Frame 7 saved (frame_006.jpg, t=65.3s) [07:30] [capture-periodic] freeze=3ms shot=276ms unfreeze=3ms saved=True [07:30] Execution complete (t=65.8s) [07:30] Execution error: {'prompt_id': 'e0c035eb-f05f-41eb-84c6-6805d60bdad1', 'node_id': '12', 'node_type': 'DepthAnything_V3', 'executed': ['3', '2'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 936.80 MiB\nRequested : 223.56 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute\n output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward\n out_dict = self._forward_impl(feats, H, W, patch_start_idx)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl\n fused_main, fused_aux_pyr = self._fuse(resized_feats)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse\n out = self.scratch.refinenet1(out, l1_rn)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward\n y = self.out_conv(y)\n ^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward\n return self.forward_comfy_cast_weights(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights\n x = self._conv_forward(input, weight, bias)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward\n return F.conv2d(\n ^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 936.80 MiB\nRequested : 223.56 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['V2-Style'], 'resize_method': ['resize'], 'invert_depth': [False], 'keep_model_size': [False], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n ...,\n\n [[0.1367, 0.1367, 0.1367],\n [0.2500, 0.2500, 0.2500],\n [0.0352, 0.0352, 0.0352],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.1250, 0.1250, 0.1250],\n [0.1602, 0.1602, 0.1602],\n [0.5234, 0.5234, 0.5234],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0195, 0.0195, 0.0195],\n [0.2266, 0.2266, 0.2266],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]]]])']}, 'current_outputs': ['8', '10', '6', '13', '11', '3', '2', '12', '4', '7', '9'], 'timestamp': 1778675945035} [07:30] Capturing execution frames: advanced_3d.json [07:38] Frame 1 saved (frame_000.jpg, t=0.0s) [07:38] Validating workflow... [07:38] [ComfyUI] === /validate endpoint called === [07:38] [ComfyUI] Received JSON with keys: ['prompt'] [07:38] Queuing workflow for execution... [07:38] [ComfyUI] Prompt has 6 nodes [07:38] [ComfyUI] Node 2: LoadImage [07:38] [ComfyUI] Inputs: {"image": "kaffi.jpg"} [07:38] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [07:38] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [07:38] [ComfyUI] Node 21: DepthAnything_V3 [07:38] [ComfyUI] Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} [07:38] [ComfyUI] Node 22: DA3_ToPointCloud [07:38] [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 [07:38] [ComfyUI] Node 23: DA3_SavePointCloud [07:38] [ComfyUI] Inputs: {"filename_prefix": "pointcloud", "pointcloud": ["22", 0]} [07:38] [ComfyUI] Node 25: DA3_PreviewPointCloud [07:38] [ComfyUI] Inputs: {"file_path": ["23", 0], "color_mode": "RGB", "preview_vtk": ""} [07:38] [ComfyUI] Generated prompt_id: 284563ef-cb5a-4376-82a0-92f0b24885f8 [07:38] [ComfyUI] Calling execution.validate_prompt()... [07:38] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [07:38] [ComfyUI] Validation result: valid=True [07:38] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1231/ComfyUI', '/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.1/site-packages', '/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [07:38] [ComfyUI] === Validation PASSED === [07:38] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [07:38] [ComfyUI] got prompt [07:38] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py', 'abstract://comfy_worker_b16e62a691da']... [07:38] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [07:38] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_b16e62a691da (abstract, no filesystem path) [07:38] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 24106 / 24124 MB [07:38] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [07:38] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:38] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:38] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [07:38] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [07:40] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [07:40] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:40] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:40] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:40] [ComfyUI] [SubprocessWorker] sending request via socket... [07:40] [ComfyUI] [SubprocessWorker] call_id=3 sending call_method [07:40] Frame 2 saved (frame_001.jpg, t=2.4s) [07:40] [capture-periodic] freeze=3ms shot=206ms unfreeze=6ms saved=True [07:40] [ComfyUI] [SubprocessWorker] got response: ok [07:40] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (2.51s): result: NodeOutput [07:40] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 22614 / 24124 MB [07:40] [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 [07:40] [ComfyUI] [VRAM] Before DepthAnything_V3: 22614 / 24124 MB [07:40] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [07:40] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:40] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:40] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:41] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:41] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 533, 800, 3]) [07:41] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:41] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:41] [ComfyUI] [SubprocessWorker] sending request via socket... [07:41] [ComfyUI] [SubprocessWorker] call_id=4 sending call_method [07:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 533, 800, 3] [07:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 533, 800, 3]) [07:41] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [07:43] Frame 3 saved (frame_002.jpg, t=4.7s) [07:43] [capture-periodic] freeze=4ms shot=205ms unfreeze=5ms saved=True [07:44] [capture-loop] iter=50 t=6.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=23.4/31.2GB (75%) swap=21.8/32.0GB (68%) cpu=6% browser_rss=0.91GB [07:44] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=4 [07:44] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 1.58GB [07:44] [ComfyUI] [comfy-env] VRAM after eviction: 1.58GB [07:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +267MB (now 267MB) reserved=288MB peak=267MB [07:46] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +206MB (now 473MB) reserved=576MB peak=473MB [07:46] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=4 [07:46] [ComfyUI] [SubprocessWorker] got response: ok [07:46] [ComfyUI] [comfy-env] DepthAnything_V3 done (6.04s): result: NodeOutput [07:47] [ComfyUI] [VRAM] After DepthAnything_V3: 24042 / 24124 MB [07:47] [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 [07:47] [ComfyUI] [VRAM] Before DA3_ToPointCloud: 24042 / 24124 MB [07:47] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_ToPointCloud.EXECUTE_NORMALIZED [07:47] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:47] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:47] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:47] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:47] [ComfyUI] [comfy-env] PRE-SERIALIZE 'depth_raw' shape: torch.Size([1, 532, 800, 3]) [07:47] [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 532, 800, 3]) [07:47] [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 532, 800]) [07:47] [ComfyUI] [comfy-env] PRE-SERIALIZE 'source_image' shape: torch.Size([1, 532, 800, 3]) [07:47] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:47] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:47] [ComfyUI] [SubprocessWorker] sending request via socket... [07:47] [ComfyUI] [SubprocessWorker] call_id=5 sending call_method [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800]) [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3]) [07:47] [ComfyUI] [SubprocessWorker] got response: ok [07:47] [ComfyUI] [comfy-env] DA3_ToPointCloud done (0.25s): result: NodeOutput [07:47] [ComfyUI] [VRAM] After DA3_ToPointCloud: 24042 / 24124 MB [07:47] [ComfyUI] [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1] [07:47] [ComfyUI] [VRAM] Before DA3_SavePointCloud: 24042 / 24124 MB [07:47] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED [07:47] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:47] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:47] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:47] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:47] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:47] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:47] [ComfyUI] [SubprocessWorker] sending request via socket... [07:47] [ComfyUI] [SubprocessWorker] call_id=6 sending call_method [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311069, 3] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311069, 3]) [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311069] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311069]) [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311069, 3] [07:47] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311069, 3]) [07:47] Frame 4 saved (frame_003.jpg, t=9.3s) [07:47] [capture-periodic] freeze=3ms shot=199ms unfreeze=7ms saved=True [07:50] [ComfyUI] [SubprocessWorker] got response: ok [07:50] [ComfyUI] [comfy-env] DA3_SavePointCloud done (3.00s): result: NodeOutput [07:50] [ComfyUI] [VRAM] After DA3_SavePointCloud: 24042 / 24124 MB [07:50] [ComfyUI] [comfy-env] Running DA3_PreviewPointCloud: file_path: '/workspaces/DepthAnythingV3-1231/ComfyUI/output/pointclo..., color_mode: 'RGB' [07:50] [ComfyUI] [VRAM] Before DA3_PreviewPointCloud: 24042 / 24124 MB [07:50] [ComfyUI] [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED [07:50] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [07:50] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [07:50] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [07:50] [ComfyUI] [SubprocessWorker] worker started/confirmed [07:50] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [07:50] [ComfyUI] [SubprocessWorker] created 0 shm blocks [07:50] [ComfyUI] [SubprocessWorker] sending request via socket... [07:50] [ComfyUI] [SubprocessWorker] call_id=7 sending call_method [07:50] [ComfyUI] [SubprocessWorker] got response: ok [07:50] [ComfyUI] [comfy-env] DA3_PreviewPointCloud done (0.07s): result: NodeOutput [07:50] [ComfyUI] [VRAM] After DA3_PreviewPointCloud: 24042 / 24124 MB [07:50] [ComfyUI] Prompt executed in 11.91 seconds [07:50] [capture-loop] iter=100 t=12.2s state={'complete': False, 'error': None, 'executedCount': 2, 'wsState': 1} eval_ms=17 ram=24.0/31.2GB (77%) swap=21.8/32.0GB (68%) cpu=6% browser_rss=0.91GB [07:50] Node executed (2 total), capturing... [07:52] Frame 5 saved (frame_004.jpg, t=12.4s) [07:52] [capture-node] freeze=4ms shot=253ms unfreeze=1226ms saved=True [07:52] Execution complete (t=14.1s) [07:52] Captured 5 unique frames over 14.1s [07:52] [debug] iframes: 1 [07:52] [debug] iframe[0]: src=http://127.0.0.1:41884/extensions/ComfyUI-DepthAnythingV3/viewer_vtk.html?v=1778, canvas=486x394, rafFrozen=False [07:52] [timing] trigger_3d_previews: 0.0s [07:54] Saved high-quality screenshot: advanced_3d_executed.png [07:54] [timing] final_screenshot: 0.5s [07:55] Capturing execution frames: advanced_3d_multiview.json [08:02] Frame 1 saved (frame_000.jpg, t=0.0s) [08:02] Validating workflow... [08:02] [ComfyUI] === /validate endpoint called === [08:02] [ComfyUI] Received JSON with keys: ['prompt'] [08:02] [ComfyUI] Prompt has 8 nodes [08:02] Queuing workflow for execution... [08:02] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [08:02] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [08:02] [ComfyUI] Node 21: LoadImageDataSetFromFolder [08:02] [ComfyUI] Inputs: {"folder": "SOH"} [08:02] [ComfyUI] Node 27: PreviewImage [08:02] [ComfyUI] Inputs: {"images": ["21", 0]} [08:02] [ComfyUI] Node 38: DA3_MultiViewPointCloud [08:02] [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": [08:02] [ComfyUI] Node 39: DepthAnythingV3_MultiView [08:02] [ComfyUI] Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["21", 0]} [08:02] [ComfyUI] Node 44: DA3_SavePointCloud [08:02] [ComfyUI] Inputs: {"filename_prefix": "pointcloud", "pointcloud": ["38", 0]} [08:02] [ComfyUI] Node 45: PreviewAny [08:02] [ComfyUI] Inputs: {"source": ["44", 0]} [08:02] [ComfyUI] Node 48: DA3_PreviewPointCloud [08:02] [ComfyUI] Inputs: {"file_path": ["44", 0], "color_mode": "RGB", "preview_vtk": ""} [08:02] [ComfyUI] Generated prompt_id: bff03c41-a1dd-4587-8a3e-de4d30aa9d99 [08:02] [ComfyUI] Calling execution.validate_prompt()... [08:02] [ComfyUI] Validation result: valid=True [08:02] [ComfyUI] === Validation PASSED === [08:02] [ComfyUI] got prompt [08:02] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [08:02] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 24042 / 24124 MB [08:02] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [08:02] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [08:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [08:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [08:02] [ComfyUI] [SubprocessWorker] worker started/confirmed [08:02] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [08:02] [ComfyUI] [SubprocessWorker] created 0 shm blocks [08:02] [ComfyUI] [SubprocessWorker] sending request via socket... [08:02] [ComfyUI] [SubprocessWorker] call_id=8 sending call_method [08:02] Node executed (1 total), capturing... [08:02] [ComfyUI] [SubprocessWorker] got response: ok [08:02] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (0.11s): result: NodeOutput [08:02] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 24042 / 24124 MB [08:02] [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 [08:02] [ComfyUI] [VRAM] Before DepthAnythingV3_MultiView: 24042 / 24124 MB [08:02] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [08:02] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [08:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [08:02] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [08:02] [ComfyUI] [SubprocessWorker] worker started/confirmed [08:02] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 680, 1208, 3]) [08:02] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [08:02] [ComfyUI] [SubprocessWorker] created 0 shm blocks [08:02] [ComfyUI] [SubprocessWorker] sending request via socket... [08:02] [ComfyUI] [SubprocessWorker] call_id=9 sending call_method [08:02] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [08:02] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 680, 1208, 3] [08:02] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 680, 1208, 3]) [08:02] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=9 [08:02] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 0.09GB [08:02] [ComfyUI] [comfy-env] VRAM after eviction: 0.09GB [08:02] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -270MB (now 203MB) reserved=320MB peak=522MB [08:03] Frame 2 saved (frame_001.jpg, t=0.9s) [08:03] [capture-node] freeze=4ms shot=209ms unfreeze=3ms saved=True [08:03] [ComfyUI] [SubprocessWorker] got response: error [08:03] [ComfyUI] !!! Exception during processing !!! Allocation on device 0 would exceed allowed memory. (out of memory) [08:03] [ComfyUI] Currently allocated : 978.65 MiB [08:03] [ComfyUI] Requested : 263.38 MiB [08:03] [ComfyUI] Device limit : 23.56 GiB [08:03] [ComfyUI] Free (according to CUDA): 18.25 MiB [08:03] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [08:03] [ComfyUI] : 17179869184.00 GiB [08:03] [ComfyUI] [08:03] [ComfyUI] Worker traceback: [08:03] [ComfyUI] Traceback (most recent call last): [08:03] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [08:03] [ComfyUI] result = method(**inputs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [08:03] [ComfyUI] to_return = cls.execute(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_multiview.py", line 128, in execute [08:03] [ComfyUI] output = model(normalized_images.to(device, dtype=dtype), infer_gs=infer_gs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:03] [ComfyUI] return self._call_impl(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:03] [ComfyUI] return forward_call(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [08:03] [ComfyUI] output = self._process_depth_head(feats, H, W) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [08:03] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:03] [ComfyUI] return self._call_impl(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:03] [ComfyUI] return forward_call(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] Execution complete (t=1.5s) [08:03] Execution error: {'prompt_id': '8f73df27-f7c5-4f4f-a571-710b7614e2ce', 'node_id': '39', 'node_type': 'DepthAnythingV3_MultiView', 'executed': ['21', '27', '3'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 978.65 MiB\nRequested : 263.38 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_multiview.py", line 128, in execute\n output = model(normalized_images.to(device, dtype=dtype), infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward\n out_dict = self._forward_impl(feats, H, W, patch_start_idx)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl\n fused_main, fused_aux_pyr = self._fuse(resized_feats)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse\n out = self.scratch.refinenet1(out, l1_rn)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward\n y = self.out_conv(y)\n ^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward\n return self.forward_comfy_cast_weights(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights\n x = self._conv_forward(input, weight, bias)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward\n return F.conv2d(\n ^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 978.65 MiB\nRequested : 263.38 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['Raw'], 'resize_method': ['resize'], 'invert_depth': [False], 'keep_model_size': [False], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.6157, 0.8706, 1.0000],\n [0.6157, 0.8706, 1.0000],\n [0.6118, 0.8706, 1.0000],\n ...,\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000]],\n\n [[0.6157, 0.8706, 1.0000],\n [0.6157, 0.8706, 1.0000],\n [0.6118, 0.8706, 1.0000],\n ...,\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000]],\n\n [[0.6118, 0.8706, 1.0000],\n [0.6118, 0.8706, 1.0000],\n [0.6118, 0.8706, 1.0000],\n ...,\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000]],\n\n ...,\n\n [[0.3216, 0.4157, 0.4941],\n [0.3216, 0.4157, 0.4941],\n [0.3294, 0.4118, 0.4863],\n ...,\n [0.2863, 0.4039, 0.4980],\n [0.3098, 0.4275, 0.5216],\n [0.3333, 0.4510, 0.5451]],\n\n [[0.3255, 0.4196, 0.4980],\n [0.3216, 0.4157, 0.4941],\n [0.3294, 0.4118, 0.4863],\n ...,\n [0.2275, 0.3451, 0.4392],\n [0.2039, 0.3216, 0.4157],\n [0.2157, 0.3333, 0.4275]],\n\n [[0.3176, 0.4118, 0.4902],\n [0.3216, 0.4157, 0.4941],\n [0.3255, 0.4078, 0.4824],\n ...,\n [0.3137, 0.4314, 0.5255],\n [0.3059, 0.4235, 0.5176],\n [0.2863, 0.4039, 0.4980]]]])', 'tensor([[[[0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n ...,\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000]],\n\n [[0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n ...,\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000]],\n\n [[0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n ...,\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000]],\n\n ...,\n\n [[0.3686, 0.4078, 0.4784],\n [0.3725, 0.4118, 0.4824],\n [0.3686, 0.4078, 0.4784],\n ...,\n [0.2745, 0.4039, 0.4941],\n [0.2941, 0.4235, 0.5137],\n [0.2980, 0.4275, 0.5176]],\n\n [[0.3647, 0.4039, 0.4745],\n [0.3608, 0.4000, 0.4706],\n [0.3647, 0.4039, 0.4745],\n ...,\n [0.3020, 0.4314, 0.5216],\n [0.3255, 0.4549, 0.5451],\n [0.3333, 0.4627, 0.5529]],\n\n [[0.3569, 0.3961, 0.4667],\n [0.3569, 0.3961, 0.4667],\n [0.3569, 0.3961, 0.4667],\n ...,\n [0.3176, 0.4471, 0.5373],\n [0.2941, 0.4235, 0.5137],\n [0.2902, 0.4196, 0.5098]]]])']}, 'current_outputs': ['45', '27', '21', '38', '3', '44', '48', '39'], 'timestamp': 1778675978580} [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward [08:03] [ComfyUI] out_dict = self._forward_impl(feats, H, W, patch_start_idx) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl [08:03] [ComfyUI] fused_main, fused_aux_pyr = self._fuse(resized_feats) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse [08:03] [ComfyUI] out = self.scratch.refinenet1(out, l1_rn) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:03] [ComfyUI] return self._call_impl(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:03] [ComfyUI] return forward_call(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward [08:03] [ComfyUI] y = self.out_conv(y) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:03] [ComfyUI] return self._call_impl(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:03] [ComfyUI] return forward_call(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward [08:03] [ComfyUI] return self.forward_comfy_cast_weights(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights [08:03] [ComfyUI] x = self._conv_forward(input, weight, bias) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward [08:03] [ComfyUI] return F.conv2d( [08:03] [ComfyUI] ^^^^^^^^^ [08:03] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [08:03] [ComfyUI] Currently allocated : 978.65 MiB [08:03] [ComfyUI] Requested : 263.38 MiB [08:03] [ComfyUI] Device limit : 23.56 GiB [08:03] [ComfyUI] Free (according to CUDA): 18.25 MiB [08:03] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [08:03] [ComfyUI] : 17179869184.00 GiB [08:03] [ComfyUI] [08:03] [ComfyUI] Traceback (most recent call last): [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute [08:03] [ComfyUI] output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data [08:03] [ComfyUI] return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list [08:03] [ComfyUI] await process_inputs(input_dict, i) [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs [08:03] [ComfyUI] result = f(**inputs) [08:03] [ComfyUI] ^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy [08:03] [ComfyUI] result = worker.call_method( [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method [08:03] [ComfyUI] raise WorkerError( [08:03] [ComfyUI] comfy_env.isolation.workers.base.WorkerError: Allocation on device 0 would exceed allowed memory. (out of memory) [08:03] [ComfyUI] Currently allocated : 978.65 MiB [08:03] [ComfyUI] Requested : 263.38 MiB [08:03] [ComfyUI] Device limit : 23.56 GiB [08:03] [ComfyUI] Free (according to CUDA): 18.25 MiB [08:03] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [08:03] [ComfyUI] : 17179869184.00 GiB [08:03] [ComfyUI] [08:03] [ComfyUI] Worker traceback: [08:03] [ComfyUI] Traceback (most recent call last): [08:03] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [08:03] [ComfyUI] result = method(**inputs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [08:03] [ComfyUI] to_return = cls.execute(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_multiview.py", line 128, in execute [08:03] [ComfyUI] output = model(normalized_images.to(device, dtype=dtype), infer_gs=infer_gs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:03] [ComfyUI] return self._call_impl(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:03] [ComfyUI] return forward_call(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [08:03] [ComfyUI] output = self._process_depth_head(feats, H, W) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [08:03] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:03] [ComfyUI] return self._call_impl(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:03] [ComfyUI] return forward_call(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward [08:03] [ComfyUI] out_dict = self._forward_impl(feats, H, W, patch_start_idx) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl [08:03] [ComfyUI] fused_main, fused_aux_pyr = self._fuse(resized_feats) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse [08:03] [ComfyUI] out = self.scratch.refinenet1(out, l1_rn) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:03] [ComfyUI] return self._call_impl(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:03] [ComfyUI] return forward_call(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward [08:03] [ComfyUI] y = self.out_conv(y) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:03] [ComfyUI] return self._call_impl(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:03] [ComfyUI] return forward_call(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward [08:03] [ComfyUI] return self.forward_comfy_cast_weights(*args, **kwargs) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights [08:03] [ComfyUI] x = self._conv_forward(input, weight, bias) [08:03] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:03] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward [08:03] [ComfyUI] return F.conv2d( [08:03] [ComfyUI] ^^^^^^^^^ [08:03] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [08:03] [ComfyUI] Currently allocated : 978.65 MiB [08:03] [ComfyUI] Requested : 263.38 MiB [08:03] [ComfyUI] Device limit : 23.56 GiB [08:03] [ComfyUI] Free (according to CUDA): 18.25 MiB [08:03] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [08:03] [ComfyUI] : 17179869184.00 GiB [08:03] [ComfyUI] [08:03] [ComfyUI] [08:03] [ComfyUI] Prompt executed in 1.07 seconds [08:03] Capturing execution frames: bas_relief.json [08:12] Frame 1 saved (frame_000.jpg, t=0.0s) [08:12] Validating workflow... [08:12] [ComfyUI] === /validate endpoint called === [08:12] [ComfyUI] Received JSON with keys: ['prompt'] [08:12] [ComfyUI] Prompt has 6 nodes [08:12] Queuing workflow for execution... [08:12] [ComfyUI] Node 2: LoadImage [08:12] [ComfyUI] Inputs: {"image": "bas_relief.png"} [08:12] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [08:12] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [08:12] [ComfyUI] Node 21: DepthAnything_V3 [08:12] [ComfyUI] Inputs: {"normalization_mode": "Raw", "resize_method": "resize", "invert_depth": false, "keep_model_size": true, "da3_model": ["3", 0], "images": ["2", 0]} [08:12] [ComfyUI] Node 27: PreviewImage [08:12] [ComfyUI] Inputs: {"images": ["21", 2]} [08:12] [ComfyUI] Node 30: Preview3D [08:12] [ComfyUI] Inputs: {"model_file": ["32", 0], "image": ""} [08:12] [ComfyUI] Node 32: DA3_ToMesh [08:12] [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 [08:12] [ComfyUI] Generated prompt_id: ffad7df7-dbd5-448d-891c-f9c26cd27f3f [08:12] [ComfyUI] Calling execution.validate_prompt()... [08:12] [ComfyUI] Validation result: valid=True [08:12] [ComfyUI] === Validation PASSED === [08:12] [ComfyUI] got prompt [08:12] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [08:12] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 24106 / 24124 MB [08:12] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [08:12] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [08:12] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [08:12] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [08:12] [ComfyUI] [SubprocessWorker] worker started/confirmed [08:12] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [08:12] [ComfyUI] [SubprocessWorker] created 0 shm blocks [08:12] [ComfyUI] [SubprocessWorker] sending request via socket... [08:12] [ComfyUI] [SubprocessWorker] call_id=10 sending call_method [08:12] [ComfyUI] [SubprocessWorker] got response: ok [08:12] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (0.10s): result: NodeOutput [08:12] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 24106 / 24124 MB [08:12] [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 [08:12] [ComfyUI] [VRAM] Before DepthAnything_V3: 24106 / 24124 MB [08:12] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [08:12] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [08:12] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [08:12] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [08:12] [ComfyUI] [SubprocessWorker] worker started/confirmed [08:12] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 2000, 1336, 3]) [08:12] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [08:12] [ComfyUI] [SubprocessWorker] created 0 shm blocks [08:12] [ComfyUI] [SubprocessWorker] sending request via socket... [08:12] [ComfyUI] [SubprocessWorker] call_id=11 sending call_method [08:12] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [08:12] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 2000, 1336, 3] [08:12] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 2000, 1336, 3]) [08:12] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=11 [08:12] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 0.02GB [08:12] [ComfyUI] [comfy-env] VRAM after eviction: 0.02GB [08:13] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +380MB (now 583MB) reserved=768MB peak=583MB [08:13] [ComfyUI] [SubprocessWorker] got response: error [08:13] [ComfyUI] !!! Exception during processing !!! Allocation on device 0 would exceed allowed memory. (out of memory) [08:13] [ComfyUI] Currently allocated : 1.09 GiB [08:13] [ComfyUI] Requested : 53.07 MiB [08:13] [ComfyUI] Device limit : 23.56 GiB [08:13] [ComfyUI] Free (according to CUDA): 18.25 MiB [08:13] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [08:13] [ComfyUI] : 17179869184.00 GiB [08:13] [ComfyUI] [08:13] [ComfyUI] Worker traceback: [08:13] [ComfyUI] Traceback (most recent call last): [08:13] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [08:13] [ComfyUI] result = method(**inputs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [08:13] [ComfyUI] to_return = cls.execute(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute [08:13] [ComfyUI] output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:13] [ComfyUI] return self._call_impl(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:13] [ComfyUI] return forward_call(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [08:13] [ComfyUI] output = self._process_depth_head(feats, H, W) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [08:13] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:13] [ComfyUI] return self._call_impl(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] Execution complete (t=2.0s) [08:13] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:13] Execution error: {'prompt_id': 'e951a077-cc16-4dfa-95b5-0f19db309842', 'node_id': '21', 'node_type': 'DepthAnything_V3', 'executed': ['3', '2'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.09 GiB\nRequested : 53.07 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute\n output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward\n out_dict = self._forward_impl(feats, H, W, patch_start_idx)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1401, in _forward_impl\n x = self._add_pos_embed(x, W, H)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1477, in _add_pos_embed\n pe = position_grid_to_embed(pe, x.shape[1]) * ratio\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 131, in position_grid_to_embed\n emb = torch.cat([emb_x, emb_y], dim=-1)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.09 GiB\nRequested : 53.07 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['Raw'], 'resize_method': ['resize'], 'invert_depth': [False], 'keep_model_size': [True], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.5922, 0.4510, 0.2863],\n [0.5922, 0.4588, 0.2902],\n [0.5529, 0.4235, 0.2667],\n ...,\n [0.5373, 0.4510, 0.3373],\n [0.5176, 0.4392, 0.3216],\n [0.5059, 0.4314, 0.3216]],\n\n [[0.5686, 0.4235, 0.2745],\n [0.5451, 0.4157, 0.2627],\n [0.5373, 0.4078, 0.2627],\n ...,\n [0.5412, 0.4549, 0.3451],\n [0.5137, 0.4392, 0.3294],\n [0.5020, 0.4314, 0.3255]],\n\n [[0.4745, 0.3529, 0.2235],\n [0.4706, 0.3569, 0.2235],\n [0.4745, 0.3647, 0.2392],\n ...,\n [0.5255, 0.4314, 0.3294],\n [0.5255, 0.4471, 0.3412],\n [0.5059, 0.4353, 0.3216]],\n\n ...,\n\n [[0.5294, 0.4196, 0.3059],\n [0.5333, 0.4275, 0.2941],\n [0.5412, 0.4235, 0.2941],\n ...,\n [0.5647, 0.4275, 0.2863],\n [0.5765, 0.4431, 0.2941],\n [0.5765, 0.4353, 0.2863]],\n\n [[0.5176, 0.4078, 0.2902],\n [0.5412, 0.4392, 0.3098],\n [0.5098, 0.3922, 0.2745],\n ...,\n [0.5451, 0.4078, 0.2549],\n [0.5451, 0.4000, 0.2471],\n [0.5255, 0.3686, 0.2157]],\n\n [[0.5176, 0.4196, 0.3098],\n [0.5725, 0.4667, 0.3569],\n [0.5490, 0.4392, 0.3294],\n ...,\n [0.5373, 0.3882, 0.2353],\n [0.5176, 0.3647, 0.2078],\n [0.4745, 0.3176, 0.1765]]]])']}, 'current_outputs': ['30', '27', '21', '32', '3', '2'], 'timestamp': 1778675988895} [08:13] [ComfyUI] return forward_call(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward [08:13] [ComfyUI] out_dict = self._forward_impl(feats, H, W, patch_start_idx) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1401, in _forward_impl [08:13] [ComfyUI] x = self._add_pos_embed(x, W, H) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1477, in _add_pos_embed [08:13] [ComfyUI] pe = position_grid_to_embed(pe, x.shape[1]) * ratio [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 131, in position_grid_to_embed [08:13] [ComfyUI] emb = torch.cat([emb_x, emb_y], dim=-1) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [08:13] [ComfyUI] Currently allocated : 1.09 GiB [08:13] [ComfyUI] Requested : 53.07 MiB [08:13] [ComfyUI] Device limit : 23.56 GiB [08:13] [ComfyUI] Free (according to CUDA): 18.25 MiB [08:13] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [08:13] [ComfyUI] : 17179869184.00 GiB [08:13] [ComfyUI] [08:13] [ComfyUI] Traceback (most recent call last): [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute [08:13] [ComfyUI] output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data [08:13] [ComfyUI] return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list [08:13] [ComfyUI] await process_inputs(input_dict, i) [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs [08:13] [ComfyUI] result = f(**inputs) [08:13] [ComfyUI] ^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy [08:13] [ComfyUI] result = worker.call_method( [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method [08:13] [ComfyUI] raise WorkerError( [08:13] [ComfyUI] comfy_env.isolation.workers.base.WorkerError: Allocation on device 0 would exceed allowed memory. (out of memory) [08:13] [ComfyUI] Currently allocated : 1.09 GiB [08:13] [ComfyUI] Requested : 53.07 MiB [08:13] [ComfyUI] Device limit : 23.56 GiB [08:13] [ComfyUI] Free (according to CUDA): 18.25 MiB [08:13] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [08:13] [ComfyUI] : 17179869184.00 GiB [08:13] [ComfyUI] [08:13] [ComfyUI] Worker traceback: [08:13] [ComfyUI] Traceback (most recent call last): [08:13] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [08:13] [ComfyUI] result = method(**inputs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [08:13] [ComfyUI] to_return = cls.execute(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute [08:13] [ComfyUI] output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:13] [ComfyUI] return self._call_impl(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:13] [ComfyUI] return forward_call(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [08:13] [ComfyUI] output = self._process_depth_head(feats, H, W) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [08:13] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [08:13] [ComfyUI] return self._call_impl(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [08:13] [ComfyUI] return forward_call(*args, **kwargs) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward [08:13] [ComfyUI] out_dict = self._forward_impl(feats, H, W, patch_start_idx) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1401, in _forward_impl [08:13] [ComfyUI] x = self._add_pos_embed(x, W, H) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1477, in _add_pos_embed [08:13] [ComfyUI] pe = position_grid_to_embed(pe, x.shape[1]) * ratio [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:13] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 131, in position_grid_to_embed [08:13] [ComfyUI] emb = torch.cat([emb_x, emb_y], dim=-1) [08:13] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [08:14] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [08:14] [ComfyUI] Currently allocated : 1.09 GiB [08:14] [ComfyUI] Requested : 53.07 MiB [08:14] [ComfyUI] Device limit : 23.56 GiB [08:14] [ComfyUI] Free (according to CUDA): 18.25 MiB [08:14] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [08:14] [ComfyUI] : 17179869184.00 GiB [08:14] [ComfyUI] [08:14] [ComfyUI] [08:14] [ComfyUI] Prompt executed in 1.57 seconds [08:14] Capturing execution frames: da3_streaming.json [08:21] Frame 1 saved (frame_000.jpg, t=0.0s) [08:21] Validating workflow... [08:21] [ComfyUI] === /validate endpoint called === [08:21] [ComfyUI] Received JSON with keys: ['prompt'] [08:21] Queuing workflow for execution... [08:21] [ComfyUI] Prompt has 5 nodes [08:21] [ComfyUI] Node 2: DownloadAndLoadDepthAnythingV3Model [08:21] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [08:21] [ComfyUI] Node 3: LoadVideo [08:21] [ComfyUI] Inputs: {"file": "robot_unitree.mp4", "video-preview": ""} [08:21] [ComfyUI] Node 4: SaveVideo [08:21] [ComfyUI] Inputs: {"filename_prefix": "video/preview_da3", "format": "auto", "codec": "auto", "video": ["6", 0]} [08:21] [ComfyUI] Node 5: LoadSALADModel [08:21] [ComfyUI] Inputs: {} [08:21] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [08:21] [ComfyUI] Node 6: DepthAnythingV3_Streaming [08:21] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1231/ComfyUI', '/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.1/site-packages', '/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [08:21] [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 [08:21] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [08:21] [ComfyUI] Generated prompt_id: ffe6fd91-1e21-46b9-864a-4cde5948a389 [08:21] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py', 'abstract://comfy_worker_8bf0e56c5d2a']... [08:21] [ComfyUI] Calling execution.validate_prompt()... [08:21] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_8bf0e56c5d2a (abstract, no filesystem path) [08:21] [ComfyUI] Validation result: valid=True [08:21] [ComfyUI] === Validation PASSED === [08:21] [ComfyUI] got prompt [08:21] [ComfyUI] [comfy-env] Running LoadSALADModel: [08:21] [ComfyUI] [VRAM] Before LoadSALADModel: 24106 / 24124 MB [08:21] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.LoadSALADModel.EXECUTE_NORMALIZED [08:21] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [08:21] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [08:21] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [08:21] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [08:24] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [08:24] [ComfyUI] [SubprocessWorker] worker started/confirmed [08:24] [ComfyUI] [SubprocessWorker] sending request via socket... [08:24] [ComfyUI] [SubprocessWorker] call_id=12 sending call_method [08:24] Frame 2 saved (frame_001.jpg, t=2.5s) [08:24] [capture-periodic] freeze=3ms shot=195ms unfreeze=7ms saved=True [08:24] [ComfyUI] [08:26] Frame 3 saved (frame_002.jpg, t=4.8s) [08:26] [capture-periodic] freeze=4ms shot=222ms unfreeze=7ms saved=True [08:27] [capture-loop] iter=50 t=6.3s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=22.7/31.2GB (73%) swap=22.1/32.0GB (69%) cpu=7% browser_rss=0.94GB [08:33] [capture-loop] iter=100 t=12.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=22.9/31.2GB (73%) swap=22.1/32.0GB (69%) cpu=6% browser_rss=0.93GB [08:39] [capture-loop] iter=150 t=18.0s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=22.9/31.2GB (74%) swap=22.1/32.0GB (69%) cpu=4% browser_rss=0.90GB [08:45] [capture-loop] iter=200 t=23.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=22.9/31.2GB (74%) swap=22.1/32.0GB (69%) cpu=6% browser_rss=0.90GB [08:51] [capture-loop] iter=250 t=29.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=23.0/31.2GB (74%) swap=22.1/32.0GB (69%) cpu=4% browser_rss=0.90GB [08:57] [capture-loop] iter=300 t=35.6s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=22.9/31.2GB (74%) swap=22.1/32.0GB (69%) cpu=4% browser_rss=0.90GB [09:03] [capture-loop] iter=350 t=41.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=22.9/31.2GB (73%) swap=22.1/32.0GB (69%) cpu=4% browser_rss=0.90GB [09:09] [capture-loop] iter=400 t=47.5s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=22.8/31.2GB (73%) swap=22.1/32.0GB (69%) cpu=5% browser_rss=0.90GB [09:14] [capture-loop] iter=450 t=53.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=23.0/31.2GB (74%) swap=22.1/32.0GB (69%) cpu=7% browser_rss=0.90GB [09:20] [capture-loop] iter=500 t=59.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=3 ram=23.0/31.2GB (74%) swap=22.1/32.0GB (69%) cpu=5% browser_rss=0.90GB [09:21] [ComfyUI] dino_salad.safetensors: 0%| | 0.00/352M [00:00 [09:22] [ComfyUI] [09:22] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] === END === [09:22] [ComfyUI] [09:22] Frame 4 saved (frame_003.jpg, t=60.6s) [09:22] [capture-periodic] freeze=2ms shot=144ms unfreeze=6ms saved=True [09:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [09:26] [capture-loop] iter=550 t=64.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=24.4/31.2GB (78%) swap=22.9/32.0GB (72%) cpu=10% browser_rss=0.91GB [09:28] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=14 [09:28] [ComfyUI] [comfy-env] VRAM request: 1.17GB, free before eviction: 1.58GB [09:28] [ComfyUI] [comfy-env] VRAM after eviction: 1.58GB [09:28] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +270MB (now 270MB) reserved=288MB peak=270MB [09:32] [capture-loop] iter=600 t=70.9s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=24.3/31.2GB (78%) swap=25.7/32.0GB (80%) cpu=11% browser_rss=0.85GB [09:33] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=14 [09:33] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +278MB (now 549MB) reserved=576MB peak=549MB [09:34] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Error running sage attention: Allocation on device 0 would exceed allowed memory. (out of memory) [09:34] [ComfyUI] Currently allocated : 1.24 GiB [09:34] [ComfyUI] Requested : 175.43 MiB [09:34] [ComfyUI] Device limit : 23.56 GiB [09:34] [ComfyUI] Free (according to CUDA): 22.25 MiB [09:34] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [09:34] [ComfyUI] : 17179869184.00 GiB, using pytorch attention instead. [09:34] [ComfyUI] [SubprocessWorker] got response: error [09:34] [ComfyUI] !!! Exception during processing !!! Allocation on device 0 would exceed allowed memory. (out of memory) [09:34] [ComfyUI] Currently allocated : 1.24 GiB [09:34] [ComfyUI] Requested : 175.43 MiB [09:34] [ComfyUI] Device limit : 23.56 GiB [09:34] [ComfyUI] Free (according to CUDA): 22.25 MiB [09:34] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [09:34] [ComfyUI] : 17179869184.00 GiB [09:34] [ComfyUI] [09:34] [ComfyUI] Worker traceback: [09:34] [ComfyUI] Traceback (most recent call last): [09:34] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [09:34] [ComfyUI] result = method(**inputs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [09:34] [ComfyUI] to_return = cls.execute(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/node.py", line 249, in execute [09:34] [ComfyUI] result = pipeline.run(normalized_images, pbar=pbar, [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 277, in run [09:34] [ComfyUI] result = self._process_chunk(normalized_images, start, end) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 330, in _process_chunk [09:34] [ComfyUI] output = self.model(chunk_input) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:34] [ComfyUI] return self._call_impl(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:34] [ComfyUI] return forward_call(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1560, in forward [09:34] [ComfyUI] feats, aux_feats = self.backbone( [09:34] [ComfyUI] ^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:34] [ComfyUI] return self._call_impl(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:34] [ComfyUI] return forward_call(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 891, in forward [09:34] [ComfyUI] return self.pretrained.get_intermediate_layers( [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 800, in get_intermediate_layers [09:34] [ComfyUI] outputs, aux_outputs = self._get_intermediate_layers_not_chunked( [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 750, in _get_intermediate_layers_not_chunked [09:34] [ComfyUI] x = self.process_attention(x, blk, "local", pos=l_pos) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 791, in process_attention [09:34] [ComfyUI] x = block(x, pos=pos, attn_mask=attn_mask) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:34] [ComfyUI] return self._call_impl(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:34] [ComfyUI] return forward_call(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 521, in forward [09:34] [ComfyUI] x = x + self.drop_path1(attn_residual_func(x, pos=pos, attn_mask=attn_mask)) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 516, in attn_residual_func [09:34] [ComfyUI] return self.ls1(self.attn(self.norm1(x), pos=pos, attn_mask=attn_mask)) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:34] [ComfyUI] return self._call_impl(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:34] [ComfyUI] return forward_call(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 453, in forward [09:34] [ComfyUI] x = optimized_attention_for_device(q.device)(q, k, v, heads=self.num_heads, skip_reshape=True) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 139, in wrapper [09:34] [ComfyUI] return func(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 579, in attention_sage [09:34] [ComfyUI] return attention_pytorch(q, k, v, heads, mask=mask, skip_reshape=True, skip_output_reshape=skip_output_reshape, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 139, in wrapper [09:34] [ComfyUI] return func(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 520, in attention_pytorch [09:34] [ComfyUI] out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False, **sdpa_extra) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 39, in scaled_dot_product_attention [09:34] [ComfyUI] return torch.nn.functional.scaled_dot_product_attention(q, k, v, *args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [09:34] [ComfyUI] Currently allocated : 1.24 GiB [09:34] [ComfyUI] Requested : 175.43 MiB [09:34] [ComfyUI] Device limit : 23.56 GiB [09:34] [ComfyUI] Free (according to CUDA): 22.25 MiB [09:34] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [09:34] [ComfyUI] : 17179869184.00 GiB [09:34] [ComfyUI] [09:34] [ComfyUI] Traceback (most recent call last): [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute [09:34] [ComfyUI] output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data [09:34] [ComfyUI] return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list [09:34] [ComfyUI] await process_inputs(input_dict, i) [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs [09:34] [ComfyUI] result = f(**inputs) [09:34] [ComfyUI] ^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy [09:34] [ComfyUI] result = worker.call_method( [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method [09:34] [ComfyUI] raise WorkerError( [09:34] [ComfyUI] comfy_env.isolation.workers.base.WorkerError: Allocation on device 0 would exceed allowed memory. (out of memory) [09:34] [ComfyUI] Currently allocated : 1.24 GiB [09:34] [ComfyUI] Requested : 175.43 MiB [09:34] [ComfyUI] Device limit : 23.56 GiB [09:34] [ComfyUI] Free (according to CUDA): 22.25 MiB [09:34] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [09:34] [ComfyUI] : 17179869184.00 GiB [09:34] [ComfyUI] [09:34] [ComfyUI] Worker traceback: [09:34] [ComfyUI] Traceback (most recent call last): [09:34] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [09:34] [ComfyUI] result = method(**inputs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [09:34] [ComfyUI] to_return = cls.execute(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/node.py", line 249, in execute [09:34] [ComfyUI] result = pipeline.run(normalized_images, pbar=pbar, [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 277, in run [09:34] [ComfyUI] result = self._process_chunk(normalized_images, start, end) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 330, in _process_chunk [09:34] [ComfyUI] output = self.model(chunk_input) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:34] [ComfyUI] return self._call_impl(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:34] [ComfyUI] return forward_call(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1560, in forward [09:34] [ComfyUI] feats, aux_feats = self.backbone( [09:34] [ComfyUI] ^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:34] [ComfyUI] return self._call_impl(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:34] [ComfyUI] return forward_call(*args, **kwargs) [09:34] Execution complete (t=73.0s) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] Execution error: {'prompt_id': 'd221db26-2dc6-46c6-bcaf-0363bb5f4cb0', 'node_id': '6', 'node_type': 'DepthAnythingV3_Streaming', 'executed': ['3', '5', '2'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.24 GiB\nRequested : 175.43 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 22.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/node.py", line 249, in execute\n result = pipeline.run(normalized_images, pbar=pbar,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 277, in run\n result = self._process_chunk(normalized_images, start, end)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 330, in _process_chunk\n output = self.model(chunk_input)\n ^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1560, in forward\n feats, aux_feats = self.backbone(\n ^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 891, in forward\n return self.pretrained.get_intermediate_layers(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 800, in get_intermediate_layers\n outputs, aux_outputs = self._get_intermediate_layers_not_chunked(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 750, in _get_intermediate_layers_not_chunked\n x = self.process_attention(x, blk, "local", pos=l_pos)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 791, in process_attention\n x = block(x, pos=pos, attn_mask=attn_mask)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 521, in forward\n x = x + self.drop_path1(attn_residual_func(x, pos=pos, attn_mask=attn_mask))\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 516, in attn_residual_func\n return self.ls1(self.attn(self.norm1(x), pos=pos, attn_mask=attn_mask))\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 453, in forward\n x = optimized_attention_for_device(q.device)(q, k, v, heads=self.num_heads, skip_reshape=True)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 139, in wrapper\n return func(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 579, in attention_sage\n return attention_pytorch(q, k, v, heads, mask=mask, skip_reshape=True, skip_output_reshape=skip_output_reshape, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 139, in wrapper\n return func(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 520, in attention_pytorch\n out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False, **sdpa_extra)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 39, in scaled_dot_product_attention\n return torch.nn.functional.scaled_dot_product_attention(q, k, v, *args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.24 GiB\nRequested : 175.43 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 22.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_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': [0.015], 'conf_threshold_coef': [0.75], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'video': [''], 'salad_model': ["{'checkpoint_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/salad/dino_salad.safetensors'}"]}, 'current_outputs': ['6', '3', '2', '5', '4'], 'timestamp': 1778676069429} [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 891, in forward [09:34] [ComfyUI] return self.pretrained.get_intermediate_layers( [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 800, in get_intermediate_layers [09:34] [ComfyUI] outputs, aux_outputs = self._get_intermediate_layers_not_chunked( [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 750, in _get_intermediate_layers_not_chunked [09:34] [ComfyUI] x = self.process_attention(x, blk, "local", pos=l_pos) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 791, in process_attention [09:34] [ComfyUI] x = block(x, pos=pos, attn_mask=attn_mask) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:34] [ComfyUI] return self._call_impl(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:34] [ComfyUI] return forward_call(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 521, in forward [09:34] [ComfyUI] x = x + self.drop_path1(attn_residual_func(x, pos=pos, attn_mask=attn_mask)) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 516, in attn_residual_func [09:34] [ComfyUI] return self.ls1(self.attn(self.norm1(x), pos=pos, attn_mask=attn_mask)) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:34] [ComfyUI] return self._call_impl(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:34] [ComfyUI] return forward_call(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 453, in forward [09:34] [ComfyUI] x = optimized_attention_for_device(q.device)(q, k, v, heads=self.num_heads, skip_reshape=True) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 139, in wrapper [09:34] [ComfyUI] return func(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 579, in attention_sage [09:34] [ComfyUI] return attention_pytorch(q, k, v, heads, mask=mask, skip_reshape=True, skip_output_reshape=skip_output_reshape, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 139, in wrapper [09:34] [ComfyUI] return func(*args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 520, in attention_pytorch [09:34] [ComfyUI] out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False, **sdpa_extra) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 39, in scaled_dot_product_attention [09:34] [ComfyUI] return torch.nn.functional.scaled_dot_product_attention(q, k, v, *args, **kwargs) [09:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:34] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [09:34] [ComfyUI] Currently allocated : 1.24 GiB [09:34] [ComfyUI] Requested : 175.43 MiB [09:34] [ComfyUI] Device limit : 23.56 GiB [09:34] [ComfyUI] Free (according to CUDA): 22.25 MiB [09:34] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [09:34] [ComfyUI] : 17179869184.00 GiB [09:34] [ComfyUI] [09:34] [ComfyUI] [09:34] [ComfyUI] Prompt executed in 72.23 seconds [09:35] Capturing execution frames: simple.json [09:42] Frame 1 saved (frame_000.jpg, t=0.0s) [09:42] Validating workflow... [09:42] [ComfyUI] === /validate endpoint called === [09:42] [ComfyUI] Received JSON with keys: ['prompt'] [09:42] [ComfyUI] Prompt has 4 nodes [09:42] Queuing workflow for execution... [09:42] [ComfyUI] Node 2: LoadImage [09:42] [ComfyUI] Inputs: {"image": "bridge.jpg"} [09:42] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [09:42] [ComfyUI] Inputs: {"model": "da3_large.safetensors", "precision": "auto", "attention": "auto"} [09:42] [ComfyUI] Node 4: PreviewImage [09:42] [ComfyUI] Inputs: {"images": ["14", 0]} [09:42] [ComfyUI] Node 14: DepthAnything_V3 [09:42] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": true, "keep_model_size": false, "da3_model": ["3", 0], "images": ["2", 0]} [09:42] [ComfyUI] Generated prompt_id: 5f4eba2c-3b03-4087-9f28-6d42e460056e [09:42] [ComfyUI] Calling execution.validate_prompt()... [09:42] [ComfyUI] Validation result: valid=True [09:42] [ComfyUI] === Validation PASSED === [09:42] [ComfyUI] got prompt [09:42] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto' [09:42] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 24102 / 24124 MB [09:42] [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [09:42] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [09:42] [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1231/ComfyUI', '/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.1/site-packages', '/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3'] [09:42] [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python [09:42] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [09:42] [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py', 'abstract://comfy_worker_b93678a055f5']... [09:42] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:42] [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_b93678a055f5 (abstract, no filesystem path) [09:42] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed [09:42] [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker... [09:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available. [09:44] Frame 2 saved (frame_001.jpg, t=2.5s) [09:44] [capture-periodic] freeze=3ms shot=209ms unfreeze=3ms saved=True [09:44] [ComfyUI] [SubprocessWorker] worker started/confirmed [09:44] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [09:44] [ComfyUI] [SubprocessWorker] created 0 shm blocks [09:44] [ComfyUI] [SubprocessWorker] sending request via socket... [09:44] [ComfyUI] [SubprocessWorker] call_id=15 sending call_method [09:44] [ComfyUI] [SubprocessWorker] got response: ok [09:44] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (2.77s): result: NodeOutput [09:44] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 22614 / 24124 MB [09:44] [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 [09:44] [ComfyUI] [VRAM] Before DepthAnything_V3: 22614 / 24124 MB [09:44] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [09:44] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [09:44] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [09:44] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [09:44] [ComfyUI] [SubprocessWorker] worker started/confirmed [09:44] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 683, 1024, 3]) [09:44] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [09:44] [ComfyUI] [SubprocessWorker] created 0 shm blocks [09:44] [ComfyUI] [SubprocessWorker] sending request via socket... [09:44] [ComfyUI] [SubprocessWorker] call_id=16 sending call_method [09:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [09:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 683, 1024, 3] [09:44] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 683, 1024, 3]) [09:45] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions. [09:46] Frame 3 saved (frame_002.jpg, t=4.8s) [09:46] [capture-periodic] freeze=3ms shot=210ms unfreeze=2ms saved=True [09:47] [capture-loop] iter=50 t=6.2s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=4 ram=18.0/31.2GB (58%) swap=26.4/32.0GB (82%) cpu=8% browser_rss=1.03GB [09:48] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=16 [09:48] [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 1.58GB [09:48] [ComfyUI] [comfy-env] VRAM after eviction: 1.58GB [09:48] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +202MB (now 202MB) reserved=224MB peak=202MB [09:49] [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. [09:50] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +205MB (now 408MB) reserved=512MB peak=408MB [09:51] [ComfyUI] [SubprocessWorker] got response: error [09:51] [ComfyUI] !!! Exception during processing !!! Allocation on device 0 would exceed allowed memory. (out of memory) [09:51] [ComfyUI] Currently allocated : 936.80 MiB [09:51] [ComfyUI] Requested : 223.56 MiB [09:51] [ComfyUI] Device limit : 23.56 GiB [09:51] [ComfyUI] Free (according to CUDA): 18.25 MiB [09:51] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [09:51] [ComfyUI] : 17179869184.00 GiB [09:51] [ComfyUI] [09:51] [ComfyUI] Worker traceback: [09:51] [ComfyUI] Traceback (most recent call last): [09:51] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [09:51] [ComfyUI] result = method(**inputs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [09:51] [ComfyUI] to_return = cls.execute(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute [09:51] [ComfyUI] output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:51] [ComfyUI] return self._call_impl(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:51] [ComfyUI] return forward_call(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [09:51] [ComfyUI] output = self._process_depth_head(feats, H, W) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [09:51] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:51] [ComfyUI] return self._call_impl(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:51] [ComfyUI] return forward_call(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward [09:51] [ComfyUI] out_dict = self._forward_impl(feats, H, W, patch_start_idx) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl [09:51] [ComfyUI] fused_main, fused_aux_pyr = self._fuse(resized_feats) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse [09:51] [ComfyUI] out = self.scratch.refinenet1(out, l1_rn) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:51] [ComfyUI] return self._call_impl(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:51] [ComfyUI] return forward_call(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward [09:51] [ComfyUI] y = self.out_conv(y) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:51] [ComfyUI] return self._call_impl(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:51] [ComfyUI] return forward_call(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward [09:51] [ComfyUI] return self.forward_comfy_cast_weights(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights [09:51] [ComfyUI] x = self._conv_forward(input, weight, bias) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward [09:51] [ComfyUI] return F.conv2d( [09:51] [ComfyUI] ^^^^^^^^^ [09:51] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [09:51] [ComfyUI] Currently allocated : 936.80 MiB [09:51] [ComfyUI] Requested : 223.56 MiB [09:51] [ComfyUI] Device limit : 23.56 GiB [09:51] [ComfyUI] Free (according to CUDA): 18.25 MiB [09:51] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [09:51] [ComfyUI] : 17179869184.00 GiB [09:51] [ComfyUI] [09:51] [ComfyUI] Traceback (most recent call last): [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute [09:51] [ComfyUI] output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data [09:51] [ComfyUI] return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list [09:51] [ComfyUI] await process_inputs(input_dict, i) [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs [09:51] [ComfyUI] result = f(**inputs) [09:51] [ComfyUI] ^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy [09:51] [ComfyUI] result = worker.call_method( [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method [09:51] [ComfyUI] raise WorkerError( [09:51] [ComfyUI] comfy_env.isolation.workers.base.WorkerError: Allocation on device 0 would exceed allowed memory. (out of memory) [09:51] [ComfyUI] Currently allocated : 936.80 MiB [09:51] [ComfyUI] Requested : 223.56 MiB [09:51] [ComfyUI] Device limit : 23.56 GiB [09:51] [ComfyUI] Free (according to CUDA): 18.25 MiB [09:51] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [09:51] [ComfyUI] : 17179869184.00 GiB [09:51] [ComfyUI] [09:51] [ComfyUI] Worker traceback: [09:51] [ComfyUI] Traceback (most recent call last): [09:51] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [09:51] [ComfyUI] result = method(**inputs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [09:51] [ComfyUI] to_return = cls.execute(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute [09:51] [ComfyUI] output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:51] [ComfyUI] return self._call_impl(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:51] [ComfyUI] return forward_call(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [09:51] [ComfyUI] output = self._process_depth_head(feats, H, W) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [09:51] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:51] [ComfyUI] return self._call_impl(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:51] [ComfyUI] return forward_call(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward [09:51] [ComfyUI] out_dict = self._forward_impl(feats, H, W, patch_start_idx) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl [09:51] [ComfyUI] fused_main, fused_aux_pyr = self._fuse(resized_feats) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] Frame 4 saved (frame_003.jpg, t=9.3s) [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse [09:51] [capture-periodic] freeze=7ms shot=256ms unfreeze=8ms saved=True [09:51] [ComfyUI] out = self.scratch.refinenet1(out, l1_rn) [09:51] Execution complete (t=9.3s) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] Execution error: {'prompt_id': 'a0f1481b-5b89-44b7-b1bb-acbed3ea49c3', 'node_id': '14', 'node_type': 'DepthAnything_V3', 'executed': ['3', '2'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 936.80 MiB\nRequested : 223.56 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute\n output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward\n out_dict = self._forward_impl(feats, H, W, patch_start_idx)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl\n fused_main, fused_aux_pyr = self._fuse(resized_feats)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse\n out = self.scratch.refinenet1(out, l1_rn)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward\n y = self.out_conv(y)\n ^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward\n return self.forward_comfy_cast_weights(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights\n x = self._conv_forward(input, weight, bias)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward\n return F.conv2d(\n ^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 936.80 MiB\nRequested : 223.56 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['V2-Style'], 'resize_method': ['resize'], 'invert_depth': [True], 'keep_model_size': [False], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n ...,\n\n [[0.1367, 0.1367, 0.1367],\n [0.2500, 0.2500, 0.2500],\n [0.0352, 0.0352, 0.0352],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.1250, 0.1250, 0.1250],\n [0.1602, 0.1602, 0.1602],\n [0.5234, 0.5234, 0.5234],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0195, 0.0195, 0.0195],\n [0.2266, 0.2266, 0.2266],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]]]])']}, 'current_outputs': ['3', '14', '4', '2'], 'timestamp': 1778676086313} [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:51] [ComfyUI] return self._call_impl(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:51] [ComfyUI] return forward_call(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward [09:51] [ComfyUI] y = self.out_conv(y) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [09:51] [ComfyUI] return self._call_impl(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [09:51] [ComfyUI] return forward_call(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward [09:51] [ComfyUI] return self.forward_comfy_cast_weights(*args, **kwargs) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights [09:51] [ComfyUI] x = self._conv_forward(input, weight, bias) [09:51] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [09:51] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward [09:51] [ComfyUI] return F.conv2d( [09:51] [ComfyUI] ^^^^^^^^^ [09:51] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [09:51] [ComfyUI] Currently allocated : 936.80 MiB [09:51] [ComfyUI] Requested : 223.56 MiB [09:51] [ComfyUI] Device limit : 23.56 GiB [09:51] [ComfyUI] Free (according to CUDA): 18.25 MiB [09:51] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [09:51] [ComfyUI] : 17179869184.00 GiB [09:51] [ComfyUI] [09:51] [ComfyUI] [09:51] [ComfyUI] Prompt executed in 8.93 seconds [09:51] Capturing execution frames: video_multiview_depth.json [09:59] Frame 1 saved (frame_000.jpg, t=0.0s) [09:59] Validating workflow... [09:59] [ComfyUI] === /validate endpoint called === [09:59] [ComfyUI] Received JSON with keys: ['prompt'] [09:59] [ComfyUI] Prompt has 9 nodes [09:59] Queuing workflow for execution... [09:59] [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model [09:59] [ComfyUI] Inputs: {"model": "da3_base.safetensors", "precision": "auto", "attention": "auto"} [09:59] [ComfyUI] Node 52: CreateVideo [09:59] [ComfyUI] Inputs: {"fps": 10, "images": ["62", 0]} [09:59] [ComfyUI] Node 53: CreateVideo [09:59] [ComfyUI] Inputs: {"fps": 10, "images": ["61", 0]} [09:59] [ComfyUI] Node 54: SaveVideo [09:59] [ComfyUI] Inputs: {"filename_prefix": "video/ComfyUI", "format": "auto", "codec": "auto", "video": ["52", 0]} [09:59] [ComfyUI] Node 55: SaveVideo [09:59] [ComfyUI] Inputs: {"filename_prefix": "video/ComfyUI", "format": "auto", "codec": "auto", "video": ["53", 0]} [09:59] [ComfyUI] Node 61: DepthAnything_V3 [09:59] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["71", 0]} [09:59] [ComfyUI] Node 62: DepthAnythingV3_MultiView [09:59] [ComfyUI] Inputs: {"normalization_mode": "V2-Style", "resize_method": "resize", "invert_depth": false, "keep_model_size": false, "da3_model": ["3", 0], "images": ["71", 0]} [09:59] [ComfyUI] Node 66: PreviewImage [09:59] [ComfyUI] Inputs: {"images": ["71", 0]} [09:59] [ComfyUI] Node 71: LoadImagesFromFolderKJ [09:59] [ComfyUI] Inputs: {"folder": "input/robotframes", "width": 1024, "height": 576, "keep_aspect_ratio": "crop", "image_load_cap": 0, "start_index": 0, "include_subfolders": false} [09:59] [ComfyUI] Generated prompt_id: 0570c8ba-aaed-4e3f-a7ab-4fe233eca6a6 [09:59] [ComfyUI] Calling execution.validate_prompt()... [09:59] [ComfyUI] Validation result: valid=True [09:59] [ComfyUI] === Validation PASSED === [09:59] [ComfyUI] got prompt [10:00] [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_base.safetensors', precision: 'auto', attention: 'auto' [10:00] [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 24106 / 24124 MB [10:00] [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED [10:00] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [10:00] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [10:00] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [10:00] [ComfyUI] [SubprocessWorker] worker started/confirmed [10:00] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [10:00] [ComfyUI] [SubprocessWorker] created 0 shm blocks [10:00] [ComfyUI] [SubprocessWorker] sending request via socket... [10:00] [ComfyUI] [SubprocessWorker] call_id=17 sending call_method [10:00] Node executed (1 total), capturing... [10:01] [ComfyUI] [10:01] Frame 2 saved (frame_001.jpg, t=1.8s) [10:01] [capture-node] freeze=4ms shot=203ms unfreeze=10ms saved=True [10:05] [capture-loop] iter=50 t=6.4s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.5/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=6% browser_rss=1.08GB [10:05] Frame 3 saved (frame_002.jpg, t=6.4s) [10:05] [capture-periodic] freeze=4ms shot=212ms unfreeze=7ms saved=True [10:11] [capture-loop] iter=100 t=12.5s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.3/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=5% browser_rss=0.91GB [10:17] [capture-loop] iter=150 t=18.5s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.2/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=4% browser_rss=0.90GB [10:23] [capture-loop] iter=200 t=24.2s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.6/31.2GB (63%) swap=26.4/32.0GB (82%) cpu=5% browser_rss=0.88GB [10:29] [capture-loop] iter=250 t=30.2s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.6/31.2GB (63%) swap=26.4/32.0GB (82%) cpu=7% browser_rss=0.87GB [10:35] [capture-loop] iter=300 t=36.1s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.4/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=6% browser_rss=0.88GB [10:40] [capture-loop] iter=350 t=41.9s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.3/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=4% browser_rss=0.88GB [10:42] [ComfyUI] model.safetensors: 0%| | 0.00/542M [00:00 [10:42] [ComfyUI] [10:42] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] === END === [10:42] [ComfyUI] [10:42] [ComfyUI] [10:42] [ComfyUI] model.safetensors: 12%|█▏ | 67.1M/542M [00:41<04:53, 1.61MB/s][SubprocessWorker] callback 'report_progress' from call_id=17 [10:43] Frame 4 saved (frame_003.jpg, t=44.6s) [10:43] [capture-periodic] freeze=3ms shot=229ms unfreeze=25ms saved=True [10:47] [capture-loop] iter=400 t=48.0s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.3/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=4% browser_rss=0.88GB [10:53] [capture-loop] iter=450 t=54.0s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=3 ram=19.5/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=5% browser_rss=0.88GB [10:58] [capture-loop] iter=500 t=59.8s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.5/31.2GB (63%) swap=26.4/32.0GB (82%) cpu=5% browser_rss=0.88GB [11:01] [ComfyUI] [11:03] [ComfyUI] model.safetensors: 12%|█▏ | 67.1M/542M [01:00<04:53, 1.61MB/s] [11:03] [ComfyUI] model.safetensors: 50%|████▉ | 268M/542M [01:02<00:55, 4.93MB/s] [SubprocessWorker] callback 'report_progress' from call_id=17 [11:04] Frame 5 saved (frame_004.jpg, t=64.9s) [11:04] [capture-periodic] freeze=4ms shot=206ms unfreeze=8ms saved=True [11:04] [capture-loop] iter=550 t=65.8s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.4/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=6% browser_rss=0.88GB [11:10] [capture-loop] iter=600 t=71.6s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.5/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=6% browser_rss=0.88GB [11:16] [capture-loop] iter=650 t=77.6s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.4/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=6% browser_rss=0.88GB [11:21] [ComfyUI] [11:22] [capture-loop] iter=700 t=83.6s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=4 ram=19.4/31.2GB (62%) swap=26.4/32.0GB (82%) cpu=6% browser_rss=0.88GB [11:24] [ComfyUI] model.safetensors: 50%|████▉ | 268M/542M [01:20<00:55, 4.93MB/s] [11:24] [ComfyUI] model.safetensors: 62%|██████▏ | 335M/542M [01:23<00:48, 4.28MB/s][SubprocessWorker] callback 'report_progress' from call_id=17 [11:25] [ComfyUI] [11:25] [ComfyUI] model.safetensors: 74%|███████▍ | 402M/542M [01:24<00:23, 5.91MB/s][SubprocessWorker] callback 'report_progress' from call_id=17 [11:25] [ComfyUI] [11:25] [ComfyUI] model.safetensors: 100%|██████████| 542M/542M [01:24<00:00, 10.8MB/s][SubprocessWorker] callback 'report_progress' from call_id=17 [11:25] [ComfyUI] [11:25] [ComfyUI] model.safetensors: 100%|██████████| 542M/542M [01:24<00:00, 6.40MB/s] [11:25] [ComfyUI] [SubprocessWorker] got response: ok [11:25] [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (85.00s): result: NodeOutput [11:25] [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 24106 / 24124 MB [11:25] [ComfyUI] [comfy-env] Running DepthAnything_V3: normalization_mode: 'V2-Style', resize_method: 'resize', invert_depth: False, keep_model_size: False, da3_model: dict, images: torch.float32 [13,576,1024,3] cpu [11:25] [ComfyUI] [VRAM] Before DepthAnything_V3: 24106 / 24124 MB [11:25] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED [11:25] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [11:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [11:25] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [11:25] [ComfyUI] [SubprocessWorker] worker started/confirmed [11:25] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([13, 576, 1024, 3]) [11:25] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [11:25] [ComfyUI] [SubprocessWorker] created 0 shm blocks [11:25] [ComfyUI] [SubprocessWorker] sending request via socket... [11:25] [ComfyUI] [SubprocessWorker] call_id=18 sending call_method [11:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [11:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[13, 576, 1024, 3] [11:25] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([13, 576, 1024, 3]) [11:26] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=18 [11:26] [ComfyUI] [comfy-env] VRAM request: 0.27GB, free before eviction: 0.02GB [11:26] [ComfyUI] [comfy-env] VRAM after eviction: 0.02GB [11:26] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -308MB (now 100MB) reserved=352MB peak=590MB [11:26] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: This model does not support sky segmentation. V2-Style normalization will work but without sky masking. Use Mono/Metric/Nested models for best V2-Style results. [11:26] Frame 6 saved (frame_005.jpg, t=87.5s) [11:26] [capture-periodic] freeze=3ms shot=199ms unfreeze=8ms saved=True [11:28] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +243MB (now 343MB) reserved=416MB peak=590MB [11:28] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:28] [capture-loop] iter=750 t=89.5s state={'complete': False, 'error': None, 'executedCount': 1, 'wsState': 1} eval_ms=7 ram=20.2/31.2GB (65%) swap=26.4/32.0GB (82%) cpu=7% browser_rss=0.89GB [11:28] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:28] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:28] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:29] Frame 7 saved (frame_006.jpg, t=89.8s) [11:29] [capture-periodic] freeze=3ms shot=208ms unfreeze=9ms saved=True [11:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:29] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +261MB (now 604MB) reserved=1024MB peak=604MB [11:29] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:30] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:30] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:30] [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=18 [11:30] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] -381MB (now 224MB) reserved=1056MB peak=604MB [11:31] Frame 8 saved (frame_007.jpg, t=92.2s) [11:31] [capture-periodic] freeze=3ms shot=199ms unfreeze=11ms saved=True [11:32] [ComfyUI] [SubprocessWorker] got response: ok [11:32] [ComfyUI] [comfy-env] DepthAnything_V3 done (6.82s): result: NodeOutput [11:32] [ComfyUI] [VRAM] After DepthAnything_V3: 23754 / 24124 MB [11:32] [ComfyUI] [comfy-env] Running DepthAnythingV3_MultiView: normalization_mode: 'V2-Style', resize_method: 'resize', invert_depth: False, keep_model_size: False, da3_model: dict, images: torch.float32 [13,576,1024,3] cpu [11:32] [ComfyUI] [VRAM] Before DepthAnythingV3_MultiView: 23754 / 24124 MB [11:32] [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_multiview.DepthAnythingV3_MultiView.EXECUTE_NORMALIZED [11:32] [ComfyUI] [SubprocessWorker] acquired lock, ensuring started... [11:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)... [11:32] [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok [11:32] [ComfyUI] [SubprocessWorker] worker started/confirmed [11:32] [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([13, 576, 1024, 3]) [11:32] [ComfyUI] [SubprocessWorker] serializing kwargs to shm... [11:32] [ComfyUI] [SubprocessWorker] created 0 shm blocks [11:32] [ComfyUI] [SubprocessWorker] sending request via socket... [11:32] [ComfyUI] [SubprocessWorker] call_id=19 sending call_method [11:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size'] [11:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[13, 576, 1024, 3] [11:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([13, 576, 1024, 3]) [11:32] [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=19 [11:32] [ComfyUI] [comfy-env] VRAM request: 0.27GB, free before eviction: 0.39GB [11:32] [ComfyUI] [comfy-env] VRAM after eviction: 0.39GB [11:32] Node executed (2 total), capturing... [11:32] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: WARNING: This model does not support sky segmentation. V2-Style normalization will work but without sky masking. Use Mono/Metric/Nested models for best V2-Style results. [11:33] Frame 9 saved (frame_008.jpg, t=94.0s) [11:33] [capture-node] freeze=4ms shot=206ms unfreeze=3ms saved=True [11:33] [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +592MB (now 816MB) reserved=960MB peak=816MB [11:34] [ComfyUI] [SubprocessWorker] got response: error [11:34] [ComfyUI] !!! Exception during processing !!! Allocation on device 0 would exceed allowed memory. (out of memory) [11:34] [ComfyUI] Currently allocated : 1.27 GiB [11:34] [ComfyUI] Requested : 23.38 MiB [11:34] [ComfyUI] Device limit : 23.56 GiB [11:34] [ComfyUI] Free (according to CUDA): 18.25 MiB [11:34] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [11:34] [ComfyUI] : 17179869184.00 GiB [11:34] [ComfyUI] [11:34] [ComfyUI] Worker traceback: [11:34] [ComfyUI] Traceback (most recent call last): [11:34] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [11:34] [ComfyUI] result = method(**inputs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [11:34] [ComfyUI] to_return = cls.execute(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_multiview.py", line 128, in execute [11:34] [ComfyUI] output = model(normalized_images.to(device, dtype=dtype), infer_gs=infer_gs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [11:34] [ComfyUI] output = self._process_depth_head(feats, H, W) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [11:34] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1379, in forward [11:34] [ComfyUI] self._forward_impl([feat[s0:s1] for feat in feats], H, W, patch_start_idx) [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl [11:34] [ComfyUI] fused_main, fused_aux_pyr = self._fuse(resized_feats) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse [11:34] [ComfyUI] out = self.scratch.refinenet1(out, l1_rn) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 964, in forward [11:34] [ComfyUI] y = y + self.resConfUnit1(xs[1]) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 920, in forward [11:34] [ComfyUI] out = self.conv1(out) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward [11:34] [ComfyUI] return self.forward_comfy_cast_weights(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights [11:34] [ComfyUI] x = self._conv_forward(input, weight, bias) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward [11:34] [ComfyUI] return F.conv2d( [11:34] [ComfyUI] ^^^^^^^^^ [11:34] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [11:34] [ComfyUI] Currently allocated : 1.27 GiB [11:34] [ComfyUI] Requested : 23.38 MiB [11:34] [ComfyUI] Device limit : 23.56 GiB [11:34] [ComfyUI] Free (according to CUDA): 18.25 MiB [11:34] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [11:34] [ComfyUI] : 17179869184.00 GiB [11:34] [ComfyUI] [11:34] [ComfyUI] Traceback (most recent call last): [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute [11:34] [ComfyUI] output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data [11:34] [ComfyUI] return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list [11:34] [ComfyUI] await process_inputs(input_dict, i) [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs [11:34] [ComfyUI] result = f(**inputs) [11:34] [ComfyUI] ^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy [11:34] [ComfyUI] result = worker.call_method( [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method [11:34] [ComfyUI] raise WorkerError( [11:34] [ComfyUI] comfy_env.isolation.workers.base.WorkerError: Allocation on device 0 would exceed allowed memory. (out of memory) [11:34] [ComfyUI] Currently allocated : 1.27 GiB [11:34] [ComfyUI] Requested : 23.38 MiB [11:34] [ComfyUI] Device limit : 23.56 GiB [11:34] [ComfyUI] Free (according to CUDA): 18.25 MiB [11:34] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [11:34] [ComfyUI] : 17179869184.00 GiB [11:34] [ComfyUI] [11:34] [ComfyUI] Worker traceback: [11:34] [ComfyUI] Traceback (most recent call last): [11:34] [ComfyUI] File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main [11:34] [ComfyUI] result = method(**inputs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED [11:34] [ComfyUI] to_return = cls.execute(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_multiview.py", line 128, in execute [11:34] [ComfyUI] output = model(normalized_images.to(device, dtype=dtype), infer_gs=infer_gs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward [11:34] Execution complete (t=95.4s) [11:34] [ComfyUI] output = self._process_depth_head(feats, H, W) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] Execution error: {'prompt_id': 'c5aff8bd-26e2-455b-b70d-be80245ee8ea', 'node_id': '62', 'node_type': 'DepthAnythingV3_MultiView', 'executed': ['55', '61', '53', '3', '66', '71'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.27 GiB\nRequested : 23.38 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_multiview.py", line 128, in execute\n output = model(normalized_images.to(device, dtype=dtype), infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1379, in forward\n self._forward_impl([feat[s0:s1] for feat in feats], H, W, patch_start_idx)\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl\n fused_main, fused_aux_pyr = self._fuse(resized_feats)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse\n out = self.scratch.refinenet1(out, l1_rn)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 964, in forward\n y = y + self.resConfUnit1(xs[1])\n ^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 920, in forward\n out = self.conv1(out)\n ^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward\n return self.forward_comfy_cast_weights(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights\n x = self._conv_forward(input, weight, bias)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward\n return F.conv2d(\n ^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.27 GiB\nRequested : 23.38 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['V2-Style'], 'resize_method': ['resize'], 'invert_depth': [False], 'keep_model_size': [False], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_base.safetensors', 'model_key': 'da3-base', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.1333, 0.1569, 0.2314],\n [0.1333, 0.1569, 0.2314],\n [0.1294, 0.1529, 0.2275],\n ...,\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412]],\n\n [[0.1412, 0.1647, 0.2392],\n [0.1412, 0.1647, 0.2392],\n [0.1412, 0.1647, 0.2392],\n ...,\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412]],\n\n [[0.1333, 0.1451, 0.2235],\n [0.1333, 0.1451, 0.2235],\n [0.1333, 0.1451, 0.2235],\n ...,\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412]],\n\n ...,\n\n [[0.2392, 0.2510, 0.3294],\n [0.2510, 0.2627, 0.3412],\n [0.2706, 0.2824, 0.3608],\n ...,\n [0.2078, 0.2196, 0.2980],\n [0.1961, 0.2078, 0.2863],\n [0.1843, 0.1961, 0.2745]],\n\n [[0.2431, 0.2549, 0.3333],\n [0.2588, 0.2706, 0.3490],\n [0.2706, 0.2824, 0.3608],\n ...,\n [0.1961, 0.2078, 0.2784],\n [0.2039, 0.2157, 0.2863],\n [0.1922, 0.2039, 0.2745]],\n\n [[0.2471, 0.2588, 0.3373],\n [0.2627, 0.2745, 0.3529],\n [0.2784, 0.2902, 0.3686],\n ...,\n [0.1843, 0.1961, 0.2667],\n [0.1882, 0.2000, 0.2706],\n [0.1843, 0.1961, 0.2667]]],\n\n\n [[[0.1255, 0.1373, 0.2157],\n [0.1255, 0.1373, 0.2157],\n [0.1255, 0.1373, 0.2157],\n ...,\n [0.2392, 0.2627, 0.3451],\n [0.2392, 0.2627, 0.3451],\n [0.2392, 0.2627, 0.3451]],\n\n [[0.1059, 0.1176, 0.1961],\n [0.1059, 0.1176, 0.1961],\n [0.1059, 0.1176, 0.1961],\n ...,\n [0.2392, 0.2627, 0.3451],\n [0.2392, 0.2627, 0.3451],\n [0.2392, 0.2627, 0.3451]],\n\n [[0.1412, 0.1529, 0.2314],\n [0.1412, 0.1529, 0.2314],\n [0.1412, 0.1529, 0.2314],\n ...,\n [0.2431, 0.2667, 0.3490],\n [0.2431, 0.2667, 0.3490],\n [0.2431, 0.2667, 0.3490]],\n\n ...,\n\n [[0.2235, 0.2353, 0.3137],\n [0.2588, 0.2706, 0.3490],\n [0.2627, 0.2745, 0.3529],\n ...,\n [0.1882, 0.1922, 0.2667],\n [0.1843, 0.1882, 0.2627],\n [0.1843, 0.1882, 0.2627]],\n\n [[0.2471, 0.2588, 0.3373],\n [0.2392, 0.2510, 0.3294],\n [0.2353, 0.2471, 0.3255],\n ...,\n [0.1882, 0.1922, 0.2667],\n [0.1922, 0.1961, 0.2706],\n [0.1922, 0.1961, 0.2706]],\n\n [[0.2431, 0.2549, 0.3333],\n [0.2353, 0.2471, 0.3255],\n [0.2196, 0.2314, 0.3098],\n ...,\n [0.1804, 0.1843, 0.2588],\n [0.1882, 0.1922, 0.2667],\n [0.1922, 0.1961, 0.2706]]],\n\n\n [[[0.1451, 0.1686, 0.2431],\n [0.1451, 0.1686, 0.2431],\n [0.1412, 0.1647, 0.2392],\n ...,\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569]],\n\n [[0.1255, 0.1490, 0.2235],\n [0.1333, 0.1569, 0.2314],\n [0.1333, 0.1569, 0.2314],\n ...,\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569]],\n\n [[0.1294, 0.1529, 0.2275],\n [0.1412, 0.1647, 0.2392],\n [0.1451, 0.1686, 0.2431],\n ...,\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569]],\n\n ...,\n\n [[0.2510, 0.2549, 0.3373],\n [0.2627, 0.2667, 0.3490],\n [0.2627, 0.2667, 0.3490],\n ...,\n [0.1882, 0.2000, 0.2706],\n [0.2039, 0.2157, 0.2863],\n [0.1961, 0.2078, 0.2784]],\n\n [[0.2784, 0.2824, 0.3647],\n [0.2745, 0.2784, 0.3608],\n [0.2745, 0.2784, 0.3608],\n ...,\n [0.1765, 0.1882, 0.2588],\n [0.1804, 0.1922, 0.2627],\n [0.1804, 0.1922, 0.2627]],\n\n [[0.2549, 0.2588, 0.3412],\n [0.2627, 0.2667, 0.3490],\n [0.2745, 0.2784, 0.3608],\n ...,\n [0.1804, 0.1922, 0.2627],\n [0.1882, 0.2000, 0.2706],\n [0.1922, 0.2039, 0.2745]]],\n\n\n ...,\n\n\n [[[0.1098, 0.1216, 0.1922],\n [0.1098, 0.1216, 0.1922],\n [0.1098, 0.1216, 0.1922],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n [[0.1098, 0.1216, 0.1922],\n [0.1098, 0.1216, 0.1922],\n [0.1098, 0.1216, 0.1922],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n [[0.1059, 0.1176, 0.1882],\n [0.1059, 0.1176, 0.1882],\n [0.1098, 0.1216, 0.1922],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n ...,\n\n [[0.2627, 0.2667, 0.3490],\n [0.2549, 0.2588, 0.3412],\n [0.2431, 0.2471, 0.3294],\n ...,\n [0.2078, 0.2196, 0.2980],\n [0.2118, 0.2235, 0.3020],\n [0.2235, 0.2353, 0.3137]],\n\n [[0.2549, 0.2588, 0.3412],\n [0.2549, 0.2588, 0.3412],\n [0.2471, 0.2510, 0.3333],\n ...,\n [0.2078, 0.2196, 0.2980],\n [0.2118, 0.2235, 0.3020],\n [0.2314, 0.2431, 0.3216]],\n\n [[0.2627, 0.2667, 0.3490],\n [0.2549, 0.2588, 0.3412],\n [0.2471, 0.2510, 0.3333],\n ...,\n [0.2235, 0.2353, 0.3137],\n [0.2314, 0.2431, 0.3216],\n [0.2314, 0.2431, 0.3216]]],\n\n\n [[[0.1059, 0.1098, 0.1922],\n [0.1098, 0.1137, 0.1961],\n [0.1176, 0.1216, 0.2039],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n [[0.1098, 0.1137, 0.1961],\n [0.1176, 0.1216, 0.2039],\n [0.1255, 0.1294, 0.2118],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n [[0.1059, 0.1098, 0.1922],\n [0.1098, 0.1137, 0.1961],\n [0.1176, 0.1216, 0.2039],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n ...,\n\n [[0.2118, 0.2157, 0.2980],\n [0.2275, 0.2314, 0.3137],\n [0.2235, 0.2275, 0.3098],\n ...,\n [0.2039, 0.2157, 0.2941],\n [0.2078, 0.2196, 0.2980],\n [0.2157, 0.2275, 0.3059]],\n\n [[0.2745, 0.2784, 0.3608],\n [0.2902, 0.2941, 0.3765],\n [0.2471, 0.2510, 0.3333],\n ...,\n [0.2078, 0.2196, 0.2980],\n [0.2039, 0.2157, 0.2941],\n [0.2078, 0.2196, 0.2980]],\n\n [[0.2471, 0.2510, 0.3333],\n [0.2627, 0.2667, 0.3490],\n [0.2471, 0.2510, 0.3333],\n ...,\n [0.1961, 0.2078, 0.2863],\n [0.1961, 0.2078, 0.2863],\n [0.1961, 0.2078, 0.2863]]],\n\n\n [[[0.1098, 0.1137, 0.1961],\n [0.1098, 0.1137, 0.1961],\n [0.1098, 0.1137, 0.1961],\n ...,\n [0.2196, 0.2471, 0.3373],\n [0.2196, 0.2471, 0.3373],\n [0.2196, 0.2471, 0.3373]],\n\n [[0.1098, 0.1137, 0.1961],\n [0.1098, 0.1137, 0.1961],\n [0.1098, 0.1137, 0.1961],\n ...,\n [0.2196, 0.2471, 0.3373],\n [0.2196, 0.2471, 0.3373],\n [0.2196, 0.2471, 0.3373]],\n\n [[0.1059, 0.1098, 0.1922],\n [0.1059, 0.1098, 0.1922],\n [0.1059, 0.1098, 0.1922],\n ...,\n [0.2235, 0.2510, 0.3412],\n [0.2235, 0.2510, 0.3412],\n [0.2235, 0.2510, 0.3412]],\n\n ...,\n\n [[0.2078, 0.2118, 0.2941],\n [0.2078, 0.2118, 0.2941],\n [0.2196, 0.2235, 0.3059],\n ...,\n [0.2196, 0.2314, 0.3098],\n [0.2314, 0.2431, 0.3216],\n [0.2314, 0.2431, 0.3216]],\n\n [[0.2353, 0.2392, 0.3216],\n [0.2275, 0.2314, 0.3137],\n [0.2392, 0.2431, 0.3255],\n ...,\n [0.1922, 0.2039, 0.2824],\n [0.1961, 0.2078, 0.2863],\n [0.1961, 0.2078, 0.2863]],\n\n [[0.2824, 0.2863, 0.3686],\n [0.2902, 0.2941, 0.3765],\n [0.2745, 0.2784, 0.3608],\n ...,\n [0.2314, 0.2431, 0.3216],\n [0.2392, 0.2510, 0.3294],\n [0.2471, 0.2588, 0.3373]]]])']}, 'current_outputs': ['55', '61', '54', '53', '52', '3', '62', '66', '71'], 'timestamp': 1778676189344} [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head [11:34] [ComfyUI] return self.head(feats, H, W, patch_start_idx=0) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1379, in forward [11:34] [ComfyUI] self._forward_impl([feat[s0:s1] for feat in feats], H, W, patch_start_idx) [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl [11:34] [ComfyUI] fused_main, fused_aux_pyr = self._fuse(resized_feats) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse [11:34] [ComfyUI] out = self.scratch.refinenet1(out, l1_rn) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 964, in forward [11:34] [ComfyUI] y = y + self.resConfUnit1(xs[1]) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 920, in forward [11:34] [ComfyUI] out = self.conv1(out) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [11:34] [ComfyUI] return self._call_impl(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [11:34] [ComfyUI] return forward_call(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward [11:34] [ComfyUI] return self.forward_comfy_cast_weights(*args, **kwargs) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights [11:34] [ComfyUI] x = self._conv_forward(input, weight, bias) [11:34] [ComfyUI] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [11:34] [ComfyUI] File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward [11:34] [ComfyUI] return F.conv2d( [11:34] [ComfyUI] ^^^^^^^^^ [11:34] [ComfyUI] torch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory) [11:34] [ComfyUI] Currently allocated : 1.27 GiB [11:34] [ComfyUI] Requested : 23.38 MiB [11:34] [ComfyUI] Device limit : 23.56 GiB [11:34] [ComfyUI] Free (according to CUDA): 18.25 MiB [11:34] Results saved to /logs/DepthAnythingV3-1231/dev/linux-gpu/results.json [11:34] [ComfyUI] PyTorch limit (set by user-supplied memory fraction) [11:34] [ComfyUI] : 17179869184.00 GiB [11:34] [ComfyUI] [11:34] [ComfyUI] [11:34] [ComfyUI] Prompt executed in 94.69 seconds [11:34] Model report: 9 files, 2.4 GB -> /logs/DepthAnythingV3-1231/dev/linux-gpu/models.json [11:34] Saved: /logs/DepthAnythingV3-1231/dev/linux-gpu/index.html [11:34] linux: FAILED [11:34] Error: Workflow execution failed (6 error(s)) [11:34] Details: advanced.json: Workflow execution failed: {'prompt_id': 'e0c035eb-f05f-41eb-84c6-6805d60bdad1', 'node_id': '12', 'node_type': 'DepthAnything_V3', 'executed': ['3', '2'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 936.80 MiB\nRequested : 223.56 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute\n output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward\n out_dict = self._forward_impl(feats, H, W, patch_start_idx)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl\n fused_main, fused_aux_pyr = self._fuse(resized_feats)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse\n out = self.scratch.refinenet1(out, l1_rn)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward\n y = self.out_conv(y)\n ^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward\n return self.forward_comfy_cast_weights(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights\n x = self._conv_forward(input, weight, bias)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward\n return F.conv2d(\n ^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 936.80 MiB\nRequested : 223.56 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['V2-Style'], 'resize_method': ['resize'], 'invert_depth': [False], 'keep_model_size': [False], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n ...,\n\n [[0.1367, 0.1367, 0.1367],\n [0.2500, 0.2500, 0.2500],\n [0.0352, 0.0352, 0.0352],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.1250, 0.1250, 0.1250],\n [0.1602, 0.1602, 0.1602],\n [0.5234, 0.5234, 0.5234],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0195, 0.0195, 0.0195],\n [0.2266, 0.2266, 0.2266],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]]]])']}, 'current_outputs': ['8', '10', '6', '13', '11', '3', '2', '12', '4', '7', '9'], 'timestamp': 1778675945035} Details: Workflow: /node/ComfyUI-DepthAnythingV3/workflows/advanced.json Node error: DepthAnything_V3 advanced_3d_multiview.json: Workflow execution failed: {'prompt_id': '8f73df27-f7c5-4f4f-a571-710b7614e2ce', 'node_id': '39', 'node_type': 'DepthAnythingV3_MultiView', 'executed': ['21', '27', '3'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 978.65 MiB\nRequested : 263.38 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_multiview.py", line 128, in execute\n output = model(normalized_images.to(device, dtype=dtype), infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward\n out_dict = self._forward_impl(feats, H, W, patch_start_idx)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl\n fused_main, fused_aux_pyr = self._fuse(resized_feats)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse\n out = self.scratch.refinenet1(out, l1_rn)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward\n y = self.out_conv(y)\n ^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward\n return self.forward_comfy_cast_weights(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights\n x = self._conv_forward(input, weight, bias)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward\n return F.conv2d(\n ^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 978.65 MiB\nRequested : 263.38 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['Raw'], 'resize_method': ['resize'], 'invert_depth': [False], 'keep_model_size': [False], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.6157, 0.8706, 1.0000],\n [0.6157, 0.8706, 1.0000],\n [0.6118, 0.8706, 1.0000],\n ...,\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000]],\n\n [[0.6157, 0.8706, 1.0000],\n [0.6157, 0.8706, 1.0000],\n [0.6118, 0.8706, 1.0000],\n ...,\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000]],\n\n [[0.6118, 0.8706, 1.0000],\n [0.6118, 0.8706, 1.0000],\n [0.6118, 0.8706, 1.0000],\n ...,\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000],\n [0.5961, 0.8667, 1.0000]],\n\n ...,\n\n [[0.3216, 0.4157, 0.4941],\n [0.3216, 0.4157, 0.4941],\n [0.3294, 0.4118, 0.4863],\n ...,\n [0.2863, 0.4039, 0.4980],\n [0.3098, 0.4275, 0.5216],\n [0.3333, 0.4510, 0.5451]],\n\n [[0.3255, 0.4196, 0.4980],\n [0.3216, 0.4157, 0.4941],\n [0.3294, 0.4118, 0.4863],\n ...,\n [0.2275, 0.3451, 0.4392],\n [0.2039, 0.3216, 0.4157],\n [0.2157, 0.3333, 0.4275]],\n\n [[0.3176, 0.4118, 0.4902],\n [0.3216, 0.4157, 0.4941],\n [0.3255, 0.4078, 0.4824],\n ...,\n [0.3137, 0.4314, 0.5255],\n [0.3059, 0.4235, 0.5176],\n [0.2863, 0.4039, 0.4980]]]])', 'tensor([[[[0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n ...,\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000]],\n\n [[0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n ...,\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000]],\n\n [[0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n [0.6196, 0.8784, 1.0000],\n ...,\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000],\n [0.6000, 0.8784, 1.0000]],\n\n ...,\n\n [[0.3686, 0.4078, 0.4784],\n [0.3725, 0.4118, 0.4824],\n [0.3686, 0.4078, 0.4784],\n ...,\n [0.2745, 0.4039, 0.4941],\n [0.2941, 0.4235, 0.5137],\n [0.2980, 0.4275, 0.5176]],\n\n [[0.3647, 0.4039, 0.4745],\n [0.3608, 0.4000, 0.4706],\n [0.3647, 0.4039, 0.4745],\n ...,\n [0.3020, 0.4314, 0.5216],\n [0.3255, 0.4549, 0.5451],\n [0.3333, 0.4627, 0.5529]],\n\n [[0.3569, 0.3961, 0.4667],\n [0.3569, 0.3961, 0.4667],\n [0.3569, 0.3961, 0.4667],\n ...,\n [0.3176, 0.4471, 0.5373],\n [0.2941, 0.4235, 0.5137],\n [0.2902, 0.4196, 0.5098]]]])']}, 'current_outputs': ['45', '27', '21', '38', '3', '44', '48', '39'], 'timestamp': 1778675978580} Details: Workflow: /node/ComfyUI-DepthAnythingV3/workflows/advanced_3d_multiview.json Node error: DepthAnythingV3_MultiView bas_relief.json: Workflow execution failed: {'prompt_id': 'e951a077-cc16-4dfa-95b5-0f19db309842', 'node_id': '21', 'node_type': 'DepthAnything_V3', 'executed': ['3', '2'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.09 GiB\nRequested : 53.07 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute\n output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward\n out_dict = self._forward_impl(feats, H, W, patch_start_idx)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1401, in _forward_impl\n x = self._add_pos_embed(x, W, H)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1477, in _add_pos_embed\n pe = position_grid_to_embed(pe, x.shape[1]) * ratio\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 131, in position_grid_to_embed\n emb = torch.cat([emb_x, emb_y], dim=-1)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.09 GiB\nRequested : 53.07 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['Raw'], 'resize_method': ['resize'], 'invert_depth': [False], 'keep_model_size': [True], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.5922, 0.4510, 0.2863],\n [0.5922, 0.4588, 0.2902],\n [0.5529, 0.4235, 0.2667],\n ...,\n [0.5373, 0.4510, 0.3373],\n [0.5176, 0.4392, 0.3216],\n [0.5059, 0.4314, 0.3216]],\n\n [[0.5686, 0.4235, 0.2745],\n [0.5451, 0.4157, 0.2627],\n [0.5373, 0.4078, 0.2627],\n ...,\n [0.5412, 0.4549, 0.3451],\n [0.5137, 0.4392, 0.3294],\n [0.5020, 0.4314, 0.3255]],\n\n [[0.4745, 0.3529, 0.2235],\n [0.4706, 0.3569, 0.2235],\n [0.4745, 0.3647, 0.2392],\n ...,\n [0.5255, 0.4314, 0.3294],\n [0.5255, 0.4471, 0.3412],\n [0.5059, 0.4353, 0.3216]],\n\n ...,\n\n [[0.5294, 0.4196, 0.3059],\n [0.5333, 0.4275, 0.2941],\n [0.5412, 0.4235, 0.2941],\n ...,\n [0.5647, 0.4275, 0.2863],\n [0.5765, 0.4431, 0.2941],\n [0.5765, 0.4353, 0.2863]],\n\n [[0.5176, 0.4078, 0.2902],\n [0.5412, 0.4392, 0.3098],\n [0.5098, 0.3922, 0.2745],\n ...,\n [0.5451, 0.4078, 0.2549],\n [0.5451, 0.4000, 0.2471],\n [0.5255, 0.3686, 0.2157]],\n\n [[0.5176, 0.4196, 0.3098],\n [0.5725, 0.4667, 0.3569],\n [0.5490, 0.4392, 0.3294],\n ...,\n [0.5373, 0.3882, 0.2353],\n [0.5176, 0.3647, 0.2078],\n [0.4745, 0.3176, 0.1765]]]])']}, 'current_outputs': ['30', '27', '21', '32', '3', '2'], 'timestamp': 1778675988895} Details: Workflow: /node/ComfyUI-DepthAnythingV3/workflows/bas_relief.json Node error: DepthAnything_V3 da3_streaming.json: Workflow execution failed: {'prompt_id': 'd221db26-2dc6-46c6-bcaf-0363bb5f4cb0', 'node_id': '6', 'node_type': 'DepthAnythingV3_Streaming', 'executed': ['3', '5', '2'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.24 GiB\nRequested : 175.43 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 22.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/node.py", line 249, in execute\n result = pipeline.run(normalized_images, pbar=pbar,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 277, in run\n result = self._process_chunk(normalized_images, start, end)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/streaming/pipeline.py", line 330, in _process_chunk\n output = self.model(chunk_input)\n ^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1560, in forward\n feats, aux_feats = self.backbone(\n ^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 891, in forward\n return self.pretrained.get_intermediate_layers(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 800, in get_intermediate_layers\n outputs, aux_outputs = self._get_intermediate_layers_not_chunked(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 750, in _get_intermediate_layers_not_chunked\n x = self.process_attention(x, blk, "local", pos=l_pos)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 791, in process_attention\n x = block(x, pos=pos, attn_mask=attn_mask)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 521, in forward\n x = x + self.drop_path1(attn_residual_func(x, pos=pos, attn_mask=attn_mask))\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 516, in attn_residual_func\n return self.ls1(self.attn(self.norm1(x), pos=pos, attn_mask=attn_mask))\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 453, in forward\n x = optimized_attention_for_device(q.device)(q, k, v, heads=self.num_heads, skip_reshape=True)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 139, in wrapper\n return func(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 579, in attention_sage\n return attention_pytorch(q, k, v, heads, mask=mask, skip_reshape=True, skip_output_reshape=skip_output_reshape, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 139, in wrapper\n return func(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ldm/modules/attention.py", line 520, in attention_pytorch\n out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False, **sdpa_extra)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 39, in scaled_dot_product_attention\n return torch.nn.functional.scaled_dot_product_attention(q, k, v, *args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.24 GiB\nRequested : 175.43 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 22.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_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': [0.015], 'conf_threshold_coef': [0.75], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'video': [''], 'salad_model': ["{'checkpoint_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/salad/dino_salad.safetensors'}"]}, 'current_outputs': ['6', '3', '2', '5', '4'], 'timestamp': 1778676069429} Details: Workflow: /node/ComfyUI-DepthAnythingV3/workflows/da3_streaming.json Node error: DepthAnythingV3_Streaming simple.json: Workflow execution failed: {'prompt_id': 'a0f1481b-5b89-44b7-b1bb-acbed3ea49c3', 'node_id': '14', 'node_type': 'DepthAnything_V3', 'executed': ['3', '2'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 936.80 MiB\nRequested : 223.56 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_inference.py", line 156, in execute\n output = model(img, extrinsics=ext_i, intrinsics=int_i, infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1366, in forward\n out_dict = self._forward_impl(feats, H, W, patch_start_idx)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl\n fused_main, fused_aux_pyr = self._fuse(resized_feats)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse\n out = self.scratch.refinenet1(out, l1_rn)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 973, in forward\n y = self.out_conv(y)\n ^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward\n return self.forward_comfy_cast_weights(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights\n x = self._conv_forward(input, weight, bias)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward\n return F.conv2d(\n ^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 936.80 MiB\nRequested : 223.56 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['V2-Style'], 'resize_method': ['resize'], 'invert_depth': [True], 'keep_model_size': [False], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_large.safetensors', 'model_key': 'da3-large', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n ...,\n\n [[0.1367, 0.1367, 0.1367],\n [0.2500, 0.2500, 0.2500],\n [0.0352, 0.0352, 0.0352],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.1250, 0.1250, 0.1250],\n [0.1602, 0.1602, 0.1602],\n [0.5234, 0.5234, 0.5234],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]],\n\n [[0.0000, 0.0000, 0.0000],\n [0.0195, 0.0195, 0.0195],\n [0.2266, 0.2266, 0.2266],\n ...,\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000],\n [0.0000, 0.0000, 0.0000]]]])']}, 'current_outputs': ['3', '14', '4', '2'], 'timestamp': 1778676086313} Details: Workflow: /node/ComfyUI-DepthAnythingV3/workflows/simple.json Node error: DepthAnything_V3 video_multiview_depth.json: Workflow execution failed: {'prompt_id': 'c5aff8bd-26e2-455b-b70d-be80245ee8ea', 'node_id': '62', 'node_type': 'DepthAnythingV3_MultiView', 'executed': ['55', '61', '53', '3', '66', '71'], 'exception_message': 'Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.27 GiB\nRequested : 23.38 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\nWorker traceback:\nTraceback (most recent call last):\n File "/tmp/comfyui_pvenv_c1iflygq/persistent_worker.py", line 1762, in main\n result = method(**inputs)\n ^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy_api/latest/_io.py", line 1833, in EXECUTE_NORMALIZED\n to_return = cls.execute(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/nodes_multiview.py", line 128, in execute\n output = model(normalized_images.to(device, dtype=dtype), infer_gs=infer_gs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1577, in forward\n output = self._process_depth_head(feats, H, W)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1591, in _process_depth_head\n return self.head(feats, H, W, patch_start_idx=0)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1379, in forward\n self._forward_impl([feat[s0:s1] for feat in feats], H, W, patch_start_idx)\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1405, in _forward_impl\n fused_main, fused_aux_pyr = self._fuse(resized_feats)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 1465, in _fuse\n out = self.scratch.refinenet1(out, l1_rn)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 964, in forward\n y = y + self.resConfUnit1(xs[1])\n ^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3/nodes/depth_anything_v3/model.py", line 920, in forward\n out = self.conv1(out)\n ^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl\n return self._call_impl(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl\n return forward_call(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 516, in forward\n return self.forward_comfy_cast_weights(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/workspaces/DepthAnythingV3-1231/ComfyUI/comfy/ops.py", line 509, in forward_comfy_cast_weights\n x = self._conv_forward(input, weight, bias)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.11/site-packages/torch/nn/modules/conv.py", line 548, in _conv_forward\n return F.conv2d(\n ^^^^^^^^^\ntorch.OutOfMemoryError: Allocation on device 0 would exceed allowed memory. (out of memory)\nCurrently allocated : 1.27 GiB\nRequested : 23.38 MiB\nDevice limit : 23.56 GiB\nFree (according to CUDA): 18.25 MiB\nPyTorch limit (set by user-supplied memory fraction)\n : 17179869184.00 GiB\n\n', 'exception_type': 'comfy_env.isolation.workers.base.WorkerError', 'traceback': [' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 535, in execute\n output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 335, in get_output_data\n return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 309, in _async_map_node_over_list\n await process_inputs(input_dict, i)\n', ' File "/workspaces/DepthAnythingV3-1231/ComfyUI/execution.py", line 297, in process_inputs\n result = f(**inputs)\n ^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/metadata.py", line 556, in proxy\n result = worker.call_method(\n ^^^^^^^^^^^^^^^^^^^\n', ' File "/workspaces/DepthAnythingV3-1231/.venv/lib/python3.11/site-packages/comfy_env/isolation/workers/subprocess.py", line 674, in call_method\n raise WorkerError(\n'], 'current_inputs': {'normalization_mode': ['V2-Style'], 'resize_method': ['resize'], 'invert_depth': [False], 'keep_model_size': [False], 'da3_model': ["{'model_path': '/workspaces/DepthAnythingV3-1231/ComfyUI/models/depthanything3/da3_base.safetensors', 'model_key': 'da3-base', 'dtype': 'bf16', 'attention': 'auto'}"], 'images': ['tensor([[[[0.1333, 0.1569, 0.2314],\n [0.1333, 0.1569, 0.2314],\n [0.1294, 0.1529, 0.2275],\n ...,\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412]],\n\n [[0.1412, 0.1647, 0.2392],\n [0.1412, 0.1647, 0.2392],\n [0.1412, 0.1647, 0.2392],\n ...,\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412]],\n\n [[0.1333, 0.1451, 0.2235],\n [0.1333, 0.1451, 0.2235],\n [0.1333, 0.1451, 0.2235],\n ...,\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412],\n [0.2353, 0.2588, 0.3412]],\n\n ...,\n\n [[0.2392, 0.2510, 0.3294],\n [0.2510, 0.2627, 0.3412],\n [0.2706, 0.2824, 0.3608],\n ...,\n [0.2078, 0.2196, 0.2980],\n [0.1961, 0.2078, 0.2863],\n [0.1843, 0.1961, 0.2745]],\n\n [[0.2431, 0.2549, 0.3333],\n [0.2588, 0.2706, 0.3490],\n [0.2706, 0.2824, 0.3608],\n ...,\n [0.1961, 0.2078, 0.2784],\n [0.2039, 0.2157, 0.2863],\n [0.1922, 0.2039, 0.2745]],\n\n [[0.2471, 0.2588, 0.3373],\n [0.2627, 0.2745, 0.3529],\n [0.2784, 0.2902, 0.3686],\n ...,\n [0.1843, 0.1961, 0.2667],\n [0.1882, 0.2000, 0.2706],\n [0.1843, 0.1961, 0.2667]]],\n\n\n [[[0.1255, 0.1373, 0.2157],\n [0.1255, 0.1373, 0.2157],\n [0.1255, 0.1373, 0.2157],\n ...,\n [0.2392, 0.2627, 0.3451],\n [0.2392, 0.2627, 0.3451],\n [0.2392, 0.2627, 0.3451]],\n\n [[0.1059, 0.1176, 0.1961],\n [0.1059, 0.1176, 0.1961],\n [0.1059, 0.1176, 0.1961],\n ...,\n [0.2392, 0.2627, 0.3451],\n [0.2392, 0.2627, 0.3451],\n [0.2392, 0.2627, 0.3451]],\n\n [[0.1412, 0.1529, 0.2314],\n [0.1412, 0.1529, 0.2314],\n [0.1412, 0.1529, 0.2314],\n ...,\n [0.2431, 0.2667, 0.3490],\n [0.2431, 0.2667, 0.3490],\n [0.2431, 0.2667, 0.3490]],\n\n ...,\n\n [[0.2235, 0.2353, 0.3137],\n [0.2588, 0.2706, 0.3490],\n [0.2627, 0.2745, 0.3529],\n ...,\n [0.1882, 0.1922, 0.2667],\n [0.1843, 0.1882, 0.2627],\n [0.1843, 0.1882, 0.2627]],\n\n [[0.2471, 0.2588, 0.3373],\n [0.2392, 0.2510, 0.3294],\n [0.2353, 0.2471, 0.3255],\n ...,\n [0.1882, 0.1922, 0.2667],\n [0.1922, 0.1961, 0.2706],\n [0.1922, 0.1961, 0.2706]],\n\n [[0.2431, 0.2549, 0.3333],\n [0.2353, 0.2471, 0.3255],\n [0.2196, 0.2314, 0.3098],\n ...,\n [0.1804, 0.1843, 0.2588],\n [0.1882, 0.1922, 0.2667],\n [0.1922, 0.1961, 0.2706]]],\n\n\n [[[0.1451, 0.1686, 0.2431],\n [0.1451, 0.1686, 0.2431],\n [0.1412, 0.1647, 0.2392],\n ...,\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569]],\n\n [[0.1255, 0.1490, 0.2235],\n [0.1333, 0.1569, 0.2314],\n [0.1333, 0.1569, 0.2314],\n ...,\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569]],\n\n [[0.1294, 0.1529, 0.2275],\n [0.1412, 0.1647, 0.2392],\n [0.1451, 0.1686, 0.2431],\n ...,\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569],\n [0.2510, 0.2745, 0.3569]],\n\n ...,\n\n [[0.2510, 0.2549, 0.3373],\n [0.2627, 0.2667, 0.3490],\n [0.2627, 0.2667, 0.3490],\n ...,\n [0.1882, 0.2000, 0.2706],\n [0.2039, 0.2157, 0.2863],\n [0.1961, 0.2078, 0.2784]],\n\n [[0.2784, 0.2824, 0.3647],\n [0.2745, 0.2784, 0.3608],\n [0.2745, 0.2784, 0.3608],\n ...,\n [0.1765, 0.1882, 0.2588],\n [0.1804, 0.1922, 0.2627],\n [0.1804, 0.1922, 0.2627]],\n\n [[0.2549, 0.2588, 0.3412],\n [0.2627, 0.2667, 0.3490],\n [0.2745, 0.2784, 0.3608],\n ...,\n [0.1804, 0.1922, 0.2627],\n [0.1882, 0.2000, 0.2706],\n [0.1922, 0.2039, 0.2745]]],\n\n\n ...,\n\n\n [[[0.1098, 0.1216, 0.1922],\n [0.1098, 0.1216, 0.1922],\n [0.1098, 0.1216, 0.1922],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n [[0.1098, 0.1216, 0.1922],\n [0.1098, 0.1216, 0.1922],\n [0.1098, 0.1216, 0.1922],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n [[0.1059, 0.1176, 0.1882],\n [0.1059, 0.1176, 0.1882],\n [0.1098, 0.1216, 0.1922],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n ...,\n\n [[0.2627, 0.2667, 0.3490],\n [0.2549, 0.2588, 0.3412],\n [0.2431, 0.2471, 0.3294],\n ...,\n [0.2078, 0.2196, 0.2980],\n [0.2118, 0.2235, 0.3020],\n [0.2235, 0.2353, 0.3137]],\n\n [[0.2549, 0.2588, 0.3412],\n [0.2549, 0.2588, 0.3412],\n [0.2471, 0.2510, 0.3333],\n ...,\n [0.2078, 0.2196, 0.2980],\n [0.2118, 0.2235, 0.3020],\n [0.2314, 0.2431, 0.3216]],\n\n [[0.2627, 0.2667, 0.3490],\n [0.2549, 0.2588, 0.3412],\n [0.2471, 0.2510, 0.3333],\n ...,\n [0.2235, 0.2353, 0.3137],\n [0.2314, 0.2431, 0.3216],\n [0.2314, 0.2431, 0.3216]]],\n\n\n [[[0.1059, 0.1098, 0.1922],\n [0.1098, 0.1137, 0.1961],\n [0.1176, 0.1216, 0.2039],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n [[0.1098, 0.1137, 0.1961],\n [0.1176, 0.1216, 0.2039],\n [0.1255, 0.1294, 0.2118],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n [[0.1059, 0.1098, 0.1922],\n [0.1098, 0.1137, 0.1961],\n [0.1176, 0.1216, 0.2039],\n ...,\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765],\n [0.2510, 0.2784, 0.3765]],\n\n ...,\n\n [[0.2118, 0.2157, 0.2980],\n [0.2275, 0.2314, 0.3137],\n [0.2235, 0.2275, 0.3098],\n ...,\n [0.2039, 0.2157, 0.2941],\n [0.2078, 0.2196, 0.2980],\n [0.2157, 0.2275, 0.3059]],\n\n [[0.2745, 0.2784, 0.3608],\n [0.2902, 0.2941, 0.3765],\n [0.2471, 0.2510, 0.3333],\n ...,\n [0.2078, 0.2196, 0.2980],\n [0.2039, 0.2157, 0.2941],\n [0.2078, 0.2196, 0.2980]],\n\n [[0.2471, 0.2510, 0.3333],\n [0.2627, 0.2667, 0.3490],\n [0.2471, 0.2510, 0.3333],\n ...,\n [0.1961, 0.2078, 0.2863],\n [0.1961, 0.2078, 0.2863],\n [0.1961, 0.2078, 0.2863]]],\n\n\n [[[0.1098, 0.1137, 0.1961],\n [0.1098, 0.1137, 0.1961],\n [0.1098, 0.1137, 0.1961],\n ...,\n [0.2196, 0.2471, 0.3373],\n [0.2196, 0.2471, 0.3373],\n [0.2196, 0.2471, 0.3373]],\n\n [[0.1098, 0.1137, 0.1961],\n [0.1098, 0.1137, 0.1961],\n [0.1098, 0.1137, 0.1961],\n ...,\n [0.2196, 0.2471, 0.3373],\n [0.2196, 0.2471, 0.3373],\n [0.2196, 0.2471, 0.3373]],\n\n [[0.1059, 0.1098, 0.1922],\n [0.1059, 0.1098, 0.1922],\n [0.1059, 0.1098, 0.1922],\n ...,\n [0.2235, 0.2510, 0.3412],\n [0.2235, 0.2510, 0.3412],\n [0.2235, 0.2510, 0.3412]],\n\n ...,\n\n [[0.2078, 0.2118, 0.2941],\n [0.2078, 0.2118, 0.2941],\n [0.2196, 0.2235, 0.3059],\n ...,\n [0.2196, 0.2314, 0.3098],\n [0.2314, 0.2431, 0.3216],\n [0.2314, 0.2431, 0.3216]],\n\n [[0.2353, 0.2392, 0.3216],\n [0.2275, 0.2314, 0.3137],\n [0.2392, 0.2431, 0.3255],\n ...,\n [0.1922, 0.2039, 0.2824],\n [0.1961, 0.2078, 0.2863],\n [0.1961, 0.2078, 0.2863]],\n\n [[0.2824, 0.2863, 0.3686],\n [0.2902, 0.2941, 0.3765],\n [0.2745, 0.2784, 0.3608],\n ...,\n [0.2314, 0.2431, 0.3216],\n [0.2392, 0.2510, 0.3294],\n [0.2471, 0.2588, 0.3373]]]])']}, 'current_outputs': ['55', '61', '54', '53', '52', '3', '62', '66', '71'], 'timestamp': 1778676189344} Details: Workflow: /node/ComfyUI-DepthAnythingV3/workflows/video_multiview_depth.json Node error: DepthAnythingV3_MultiView [11:34] Stopping ComfyUI server...