30 lines
34 KiB
JSON
30 lines
34 KiB
JSON
{
|
|
"frames": [
|
|
{
|
|
"file": "frame_000.jpg",
|
|
"time": 0.0,
|
|
"log": " [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 3397 / 7672 MB\nCapturing execution frames: advanced_3d.json\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed\n [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker...\n [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python\n [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload)\n [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1149/ComfyUI', '/workspaces/DepthAnythingV3-1149/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.13/site-packages', '/workspaces/DepthAnythingV3-1149/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3']\n [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python\n [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_c7dez6_l/persistent_worker.py', 'abstract://comfy_worker_e38d78696170']...\n [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_e38d78696170 (abstract, no filesystem path)\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available.\n [ComfyUI] [SubprocessWorker] call_id=3 sending model_to_device\n [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 729 / 7672 MB"
|
|
},
|
|
{
|
|
"file": "frame_001.jpg",
|
|
"time": 2.35,
|
|
"log": " [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 3397 / 7672 MB\nCapturing execution frames: advanced_3d.json\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed\n [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker...\n [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python\n [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload)\n [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1149/ComfyUI', '/workspaces/DepthAnythingV3-1149/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.13/site-packages', '/workspaces/DepthAnythingV3-1149/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3']\n [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python\n [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_c7dez6_l/persistent_worker.py', 'abstract://comfy_worker_e38d78696170']...\n [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_e38d78696170 (abstract, no filesystem path)\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available.\n [ComfyUI] [SubprocessWorker] call_id=3 sending model_to_device\n [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 729 / 7672 MB\n Frame 1 saved (frame_000.jpg, t=0.0s)\n Validating workflow...\n [ComfyUI] === /validate endpoint called ===\n [ComfyUI] Received JSON with keys: ['prompt']\n [ComfyUI] Prompt has 6 nodes\n [ComfyUI] Node 2: LoadImage\n [ComfyUI] Inputs: {\"image\": \"kaffi.jpg\"}\n [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model\n Queuing workflow for execution...\n [ComfyUI] Inputs: {\"model\": \"da3_large.safetensors\", \"precision\": \"auto\", \"attention\": \"auto\"}\n [ComfyUI] Node 21: DepthAnything_V3\n [ComfyUI] Inputs: {\"normalization_mode\": \"Raw\", \"resize_method\": \"resize\", \"invert_depth\": false, \"keep_model_size\": false, \"da3_model\": [\"3\", 0], \"images\": [\"2\", 0]}\n [ComfyUI] Node 22: DA3_ToPointCloud\n [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\n [ComfyUI] Node 23: DA3_SavePointCloud\n [ComfyUI] Inputs: {\"filename_prefix\": \"pointcloud\", \"pointcloud\": [\"22\", 0]}\n [ComfyUI] Node 25: DA3_PreviewPointCloud\n [ComfyUI] Inputs: {\"file_path\": [\"23\", 0], \"color_mode\": \"RGB\", \"preview_vtk\": \"\"}\n [ComfyUI] Generated prompt_id: 5cbbfa5d-372b-46fc-9baf-286b5e5195a1\n [ComfyUI] Calling execution.validate_prompt()...\n [ComfyUI] Validation result: valid=True\n [ComfyUI] === Validation PASSED ===\n [ComfyUI] got prompt\n [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto'\n [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 729 / 7672 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=4 sending call_method\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 729 / 7672 MB\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=5 sending model_to_device\n [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 729 / 7672 MB\n [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (0.17s): result: NodeOutput\n [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 729 / 7672 MB\n [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\n [ComfyUI] [VRAM] Before DepthAnything_V3: 729 / 7672 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 533, 800, 3])\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=6 sending call_method\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 533, 800, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 533, 800, 3])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions."
|
|
},
|
|
{
|
|
"file": "frame_002.jpg",
|
|
"time": 4.61,
|
|
"log": " [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 3397 / 7672 MB\nCapturing execution frames: advanced_3d.json\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed\n [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker...\n [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python\n [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload)\n [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1149/ComfyUI', '/workspaces/DepthAnythingV3-1149/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.13/site-packages', '/workspaces/DepthAnythingV3-1149/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3']\n [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python\n [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_c7dez6_l/persistent_worker.py', 'abstract://comfy_worker_e38d78696170']...\n [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_e38d78696170 (abstract, no filesystem path)\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available.\n [ComfyUI] [SubprocessWorker] call_id=3 sending model_to_device\n [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 729 / 7672 MB\n Frame 1 saved (frame_000.jpg, t=0.0s)\n Validating workflow...\n [ComfyUI] === /validate endpoint called ===\n [ComfyUI] Received JSON with keys: ['prompt']\n [ComfyUI] Prompt has 6 nodes\n [ComfyUI] Node 2: LoadImage\n [ComfyUI] Inputs: {\"image\": \"kaffi.jpg\"}\n [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model\n Queuing workflow for execution...\n [ComfyUI] Inputs: {\"model\": \"da3_large.safetensors\", \"precision\": \"auto\", \"attention\": \"auto\"}\n [ComfyUI] Node 21: DepthAnything_V3\n [ComfyUI] Inputs: {\"normalization_mode\": \"Raw\", \"resize_method\": \"resize\", \"invert_depth\": false, \"keep_model_size\": false, \"da3_model\": [\"3\", 0], \"images\": [\"2\", 0]}\n [ComfyUI] Node 22: DA3_ToPointCloud\n [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\n [ComfyUI] Node 23: DA3_SavePointCloud\n [ComfyUI] Inputs: {\"filename_prefix\": \"pointcloud\", \"pointcloud\": [\"22\", 0]}\n [ComfyUI] Node 25: DA3_PreviewPointCloud\n [ComfyUI] Inputs: {\"file_path\": [\"23\", 0], \"color_mode\": \"RGB\", \"preview_vtk\": \"\"}\n [ComfyUI] Generated prompt_id: 5cbbfa5d-372b-46fc-9baf-286b5e5195a1\n [ComfyUI] Calling execution.validate_prompt()...\n [ComfyUI] Validation result: valid=True\n [ComfyUI] === Validation PASSED ===\n [ComfyUI] got prompt\n [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto'\n [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 729 / 7672 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=4 sending call_method\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 729 / 7672 MB\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=5 sending model_to_device\n [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 729 / 7672 MB\n [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (0.17s): result: NodeOutput\n [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 729 / 7672 MB\n [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\n [ComfyUI] [VRAM] Before DepthAnything_V3: 729 / 7672 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 533, 800, 3])\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=6 sending call_method\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 533, 800, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 533, 800, 3])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions.\n Frame 2 saved (frame_001.jpg, t=2.4s)\n [capture-periodic] freeze=2ms shot=137ms unfreeze=4ms saved=True\n [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=6\n [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 7.28GB\n [ComfyUI] [comfy-env] VRAM after eviction: 7.28GB\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +218MB (now 218MB) reserved=224MB peak=218MB\n [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=6\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +587MB (now 806MB) reserved=1888MB peak=1223MB\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1']\n [ComfyUI] [comfy-env] DepthAnything_V3 done (3.48s): result: NodeOutput\n [ComfyUI] [VRAM] After DepthAnything_V3: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [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\n [ComfyUI] [VRAM] Before DA3_ToPointCloud: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_ToPointCloud.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'depth_raw' shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 532, 800])\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'source_image' shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=7 sending call_method\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] DA3_ToPointCloud done (0.06s): result: NodeOutput\n [ComfyUI] [VRAM] After DA3_ToPointCloud: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [ComfyUI] [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1]\n [ComfyUI] [VRAM] Before DA3_SavePointCloud: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=8 sending call_method\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311405, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311405, 3])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311405]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311405])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311405, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311405, 3])"
|
|
},
|
|
{
|
|
"file": "frame_003.jpg",
|
|
"time": 6.44,
|
|
"log": " [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 3397 / 7672 MB\nCapturing execution frames: advanced_3d.json\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: failed\n [ComfyUI] [ComfyUI-DepthAnythingV3] Socket unhealthy, restarting worker...\n [ComfyUI] [ComfyUI-DepthAnythingV3] python: /root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python\n [ComfyUI] [comfy-env] Invalidated 1 stale model patchers (will be cleaned up during next unload)\n [ComfyUI] [ComfyUI-DepthAnythingV3] sys_path sent to worker: ['/workspaces/DepthAnythingV3-1149/ComfyUI', '/workspaces/DepthAnythingV3-1149/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3', '/root/.ce/.pixi/envs/depthanythingv3-nodes/lib/python3.13/site-packages', '/workspaces/DepthAnythingV3-1149/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV3']\n [ComfyUI] [SubprocessWorker] is_pixi=True, python=/root/.ce/.pixi/envs/depthanythingv3-nodes/bin/python\n [ComfyUI] [SubprocessWorker] launching cmd=['/root/.pixi/bin/pixi', 'run', '--as-is', '--manifest-path', '/root/.ce/pixi.toml', '-e', 'depthanythingv3-nodes', 'python', '/tmp/comfyui_pvenv_c7dez6_l/persistent_worker.py', 'abstract://comfy_worker_e38d78696170']...\n [ComfyUI] [SubprocessWorker] socket_addr=abstract://comfy_worker_e38d78696170 (abstract, no filesystem path)\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] ERROR: Failed to import comfy_kitchen, Error: No module named 'comfy_kitchen', fp8 and fp4 support will not be available.\n [ComfyUI] [SubprocessWorker] call_id=3 sending model_to_device\n [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 729 / 7672 MB\n Frame 1 saved (frame_000.jpg, t=0.0s)\n Validating workflow...\n [ComfyUI] === /validate endpoint called ===\n [ComfyUI] Received JSON with keys: ['prompt']\n [ComfyUI] Prompt has 6 nodes\n [ComfyUI] Node 2: LoadImage\n [ComfyUI] Inputs: {\"image\": \"kaffi.jpg\"}\n [ComfyUI] Node 3: DownloadAndLoadDepthAnythingV3Model\n Queuing workflow for execution...\n [ComfyUI] Inputs: {\"model\": \"da3_large.safetensors\", \"precision\": \"auto\", \"attention\": \"auto\"}\n [ComfyUI] Node 21: DepthAnything_V3\n [ComfyUI] Inputs: {\"normalization_mode\": \"Raw\", \"resize_method\": \"resize\", \"invert_depth\": false, \"keep_model_size\": false, \"da3_model\": [\"3\", 0], \"images\": [\"2\", 0]}\n [ComfyUI] Node 22: DA3_ToPointCloud\n [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\n [ComfyUI] Node 23: DA3_SavePointCloud\n [ComfyUI] Inputs: {\"filename_prefix\": \"pointcloud\", \"pointcloud\": [\"22\", 0]}\n [ComfyUI] Node 25: DA3_PreviewPointCloud\n [ComfyUI] Inputs: {\"file_path\": [\"23\", 0], \"color_mode\": \"RGB\", \"preview_vtk\": \"\"}\n [ComfyUI] Generated prompt_id: 5cbbfa5d-372b-46fc-9baf-286b5e5195a1\n [ComfyUI] Calling execution.validate_prompt()...\n [ComfyUI] Validation result: valid=True\n [ComfyUI] === Validation PASSED ===\n [ComfyUI] got prompt\n [ComfyUI] [comfy-env] Running DownloadAndLoadDepthAnythingV3Model: model: 'da3_large.safetensors', precision: 'auto', attention: 'auto'\n [ComfyUI] [VRAM] Before DownloadAndLoadDepthAnythingV3Model: 729 / 7672 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.load_model.DownloadAndLoadDepthAnythingV3Model.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=4 sending call_method\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 729 / 7672 MB\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=5 sending model_to_device\n [ComfyUI] Model 'DepthAnything3Net_1' gone from worker (restarted?), treating as offloaded\n [ComfyUI] [comfy-env] [VRAM] After offload 'DepthAnything3Net_1' (783 MB): 729 / 7672 MB\n [ComfyUI] [comfy-env] DownloadAndLoadDepthAnythingV3Model done (0.17s): result: NodeOutput\n [ComfyUI] [VRAM] After DownloadAndLoadDepthAnythingV3Model: 729 / 7672 MB\n [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\n [ComfyUI] [VRAM] Before DepthAnything_V3: 729 / 7672 MB\n [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_inference.DepthAnything_V3.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'images' shape: torch.Size([1, 533, 800, 3])\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=6 sending call_method\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 533, 800, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 533, 800, 3])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] WARNING: No comfy kitchen, using old apply_rope functions.\n Frame 2 saved (frame_001.jpg, t=2.4s)\n [capture-periodic] freeze=2ms shot=137ms unfreeze=4ms saved=True\n [ComfyUI] [SubprocessWorker] callback 'request_vram_budget' from call_id=6\n [ComfyUI] [comfy-env] VRAM request: 0.82GB, free before eviction: 7.28GB\n [ComfyUI] [comfy-env] VRAM after eviction: 7.28GB\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +218MB (now 218MB) reserved=224MB peak=218MB\n [ComfyUI] [SubprocessWorker] callback 'report_progress' from call_id=6\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [VRAM] +587MB (now 806MB) reserved=1888MB peak=1223MB\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] Created 1 model patchers: ['DepthAnything3Net_1']\n [ComfyUI] [comfy-env] DepthAnything_V3 done (3.48s): result: NodeOutput\n [ComfyUI] [VRAM] After DepthAnything_V3: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [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\n [ComfyUI] [VRAM] Before DA3_ToPointCloud: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_ToPointCloud.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'depth_raw' shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'confidence' shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'sky_mask' shape: torch.Size([1, 532, 800])\n [ComfyUI] [comfy-env] PRE-SERIALIZE 'source_image' shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=7 sending call_method\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[1, 532, 800, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([1, 532, 800, 3])\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] DA3_ToPointCloud done (0.06s): result: NodeOutput\n [ComfyUI] [VRAM] After DA3_ToPointCloud: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [ComfyUI] [comfy-env] Running DA3_SavePointCloud: filename_prefix: 'pointcloud', pointcloud: list[1]\n [ComfyUI] [VRAM] Before DA3_SavePointCloud: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [ComfyUI] [SubprocessWorker] call_method: nodes.nodes_3d.DA3_SavePointCloud.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=8 sending call_method\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311405, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311405, 3])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311405]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311405])\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] _from_shm got dict with keys: ['__type__', 'strategy', 'parent_pid', 'fd', 'storage_size']\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZE TensorRef: tensor_size=[311405, 3]\n [ComfyUI] [worker:ComfyUI-DepthAnythingV3] [comfy-env] DESERIALIZED tensor shape: torch.Size([311405, 3])\n Frame 3 saved (frame_002.jpg, t=4.6s)\n [capture-periodic] freeze=1ms shot=136ms unfreeze=5ms saved=True\n [capture-loop] iter=50 t=5.7s state={'complete': False, 'error': None, 'executedCount': 0, 'wsState': 1} eval_ms=2 ram=5.4/23.4GB (23%) swap=1.8/32.0GB (6%) cpu=13% browser_rss=0.92GB\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] DA3_SavePointCloud done (2.21s): result: NodeOutput\n [ComfyUI] [VRAM] After DA3_SavePointCloud: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [ComfyUI] [comfy-env] Running DA3_PreviewPointCloud: file_path: '/workspaces/DepthAnythingV3-1149/ComfyUI/output/pointclo..., color_mode: 'RGB'\n [ComfyUI] [VRAM] Before DA3_PreviewPointCloud: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [ComfyUI] [SubprocessWorker] call_method: nodes.preview_nodes.DA3_PreviewPointCloud.EXECUTE_NORMALIZED\n [ComfyUI] [SubprocessWorker] acquired lock, ensuring started...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] worker started/confirmed\n [ComfyUI] [SubprocessWorker] serializing kwargs to shm...\n [ComfyUI] [SubprocessWorker] created 0 shm blocks\n [ComfyUI] [SubprocessWorker] sending request via socket...\n [ComfyUI] [SubprocessWorker] call_id=9 sending call_method\n [ComfyUI] [SubprocessWorker] got response: ok\n [ComfyUI] [comfy-env] DA3_PreviewPointCloud done (0.01s): result: NodeOutput\n [ComfyUI] [VRAM] After DA3_PreviewPointCloud: 2725 / 7672 MB\n [ComfyUI] [VRAM] Loaded: SubprocessModel (783 MB)\n [ComfyUI] Prompt executed in 5.96 seconds\n [ComfyUI] [comfy-env] [VRAM] Before offload 'DepthAnything3Net_1' (783 MB) -> cpu: 2725 / 7672 MB\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ping (timeout=5.0s)...\n [ComfyUI] [ComfyUI-DepthAnythingV3] Health check: ok\n [ComfyUI] [SubprocessWorker] call_id=10 sending model_to_device"
|
|
},
|
|
{
|
|
"file": "frame_004.jpg",
|
|
"time": 10.015037059783936,
|
|
"log": "Final screenshot"
|
|
}
|
|
],
|
|
"total_time": 7.73
|
|
} |