## ComfyUI-Manager: installing dependencies done.
[2024-09-06 09:28] ** ComfyUI startup time: 2024-09-06 09:28:56.003091
[2024-09-06 09:28] ** Platform: Linux
[2024-09-06 09:28] ** Python version: 3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]
[2024-09-06 09:28] ** Python executable: /home/ubuntu/AI/AI_ENV/bin/python
[2024-09-06 09:28] ** ComfyUI Path: /home/ubuntu/AI/ComfyUI
[2024-09-06 09:28] ** Log path: /home/ubuntu/AI/ComfyUI/comfyui.log
[2024-09-06 09:28] 
Prestartup times for custom nodes:
[2024-09-06 09:28]    1.0 seconds: /home/ubuntu/AI/ComfyUI/custom_nodes/ComfyUI-Manager
[2024-09-06 09:28] 
Total VRAM 22516 MB, total RAM 15779 MB
[2024-09-06 09:28] pytorch version: 2.4.1+cu121
[2024-09-06 09:28] Set vram state to: NORMAL_VRAM
[2024-09-06 09:28] Device: cuda:0 NVIDIA A10G : cudaMallocAsync
[2024-09-06 09:28] Using pytorch cross attention
[2024-09-06 09:28] [Prompt Server] web root: /home/ubuntu/AI/ComfyUI/web
[2024-09-06 09:28] /home/ubuntu/AI/AI_ENV/lib/python3.10/site-packages/kornia/feature/lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
  @torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
[2024-09-06 09:28] Ib Custom Nodes: Loaded
[2024-09-06 09:28] Total VRAM 22516 MB, total RAM 15779 MB
[2024-09-06 09:28] pytorch version: 2.4.1+cu121
[2024-09-06 09:28] Set vram state to: NORMAL_VRAM
[2024-09-06 09:28] Device: cuda:0 NVIDIA A10G : cudaMallocAsync
[2024-09-06 09:28] ### Loading: ComfyUI-Manager (V2.50.3)
[2024-09-06 09:28] ### ComfyUI Revision: UNKNOWN (The currently installed ComfyUI is not a Git repository)
[2024-09-06 09:28] 
Import times for custom nodes:
[2024-09-06 09:28]    0.0 seconds: /home/ubuntu/AI/ComfyUI/custom_nodes/websocket_image_save.py
[2024-09-06 09:28]    0.0 seconds: /home/ubuntu/AI/ComfyUI/custom_nodes/ComfyUI_Ib_CustomNodes
[2024-09-06 09:28]    0.0 seconds: /home/ubuntu/AI/ComfyUI/custom_nodes/comfyui_io_helpers
[2024-09-06 09:28]    0.0 seconds: /home/ubuntu/AI/ComfyUI/custom_nodes/ComfyUI-KJNodes
[2024-09-06 09:28]    0.0 seconds: /home/ubuntu/AI/ComfyUI/custom_nodes/ComfyUI-Manager
[2024-09-06 09:28]    0.0 seconds: /home/ubuntu/AI/ComfyUI/custom_nodes/ComfyUI_essentials
[2024-09-06 09:28]    0.1 seconds: /home/ubuntu/AI/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite
[2024-09-06 09:28]    0.1 seconds: /home/ubuntu/AI/ComfyUI/custom_nodes/ComfyUI-LivePortraitKJ
[2024-09-06 09:28] 
[2024-09-06 09:28] Starting server

[2024-09-06 09:28] To see the GUI go to: http://0.0.0.0:3002
[2024-09-06 09:28] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[2024-09-06 09:28] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[2024-09-06 09:28] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[2024-09-06 09:28] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[2024-09-06 09:28] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[2024-09-06 09:29] got prompt
[2024-09-06 09:29] LivePortrait using fp16
[2024-09-06 09:29] Load appearance_feature_extractor done.
[2024-09-06 09:29] Load motion_extractor done.
[2024-09-06 09:29] Load warping_module done.
[2024-09-06 09:29] Load spade_generator done.
[2024-09-06 09:29] Load stitching_retargeting_module done.
[2024-09-06 09:29] /home/ubuntu/AI/ComfyUI/custom_nodes/ComfyUI-LivePortraitKJ/liveportrait/utils/landmark_runner.py:102: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  self.model = torch.load(ckpt_path).to(self.device)
[2024-09-06 09:29] /home/ubuntu/AI/AI_ENV/lib/python3.10/site-packages/google/protobuf/symbol_database.py:55: UserWarning: SymbolDatabase.GetPrototype() is deprecated. Please use message_factory.GetMessageClass() instead. SymbolDatabase.GetPrototype() will be removed soon.
  warnings.warn('SymbolDatabase.GetPrototype() is deprecated. Please '
[2024-09-06 09:29] 
Detecting, cropping, and processing..: 100%|██████████| 1/1 [00:00<00:00,  1.68it/s]
Detecting, cropping, and processing..: 100%|██████████| 1/1 [00:00<00:00,  1.68it/s]
[2024-09-06 09:29] 
Processing driving images...: 100%|██████████| 57/57 [00:00<00:00, 89.56it/s]
[2024-09-06 09:29] 
Animating...: 100%|██████████| 57/57 [00:03<00:00, 18.06it/s]
Animating...: 100%|██████████| 57/57 [00:03<00:00, 17.24it/s]
[2024-09-06 09:29] Total frames: 57
[2024-09-06 09:29] 
Compositing..: 100%|██████████| 57/57 [00:00<00:00, 191.62it/s]
[2024-09-06 09:29] Prompt executed in 9.90 seconds