## ComfyUI-Manager: installing dependencies done. [2025-04-08 18:08:34.070] ** ComfyUI startup time: 2025-04-08 18:08:34.070363 [2025-04-08 18:08:34.070] ** Platform: Linux [2025-04-08 18:08:34.070] ** Python version: 3.10.15 | packaged by conda-forge | (main, Sep 30 2024, 17:51:04) [GCC 13.3.0] [2025-04-08 18:08:34.070] ** Python executable: /opt/conda/envs/fuzer/bin/python [2025-04-08 18:08:34.070] ** ComfyUI Path: /home/comdoleger1/zen-flux-style-shape [2025-04-08 18:08:34.070] ** Log path: /home/comdoleger1/zen-flux-style-shape/comfyui.log [2025-04-08 18:08:35.142] Prestartup times for custom nodes: [2025-04-08 18:08:35.143] 0.0 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/rgthree-comfy [2025-04-08 18:08:35.143] 2.0 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/ComfyUI-Manager [2025-04-08 18:08:35.143] Using pytorch cross attention [2025-04-08 18:08:37.288] Could not find the extra_model_paths config file. [2025-04-08 18:08:37.292] ****** User settings have been changed to be stored on the server instead of browser storage. ****** [2025-04-08 18:08:37.292] ****** For multi-user setups add the --multi-user CLI argument to enable multiple user profiles. ****** [2025-04-08 18:08:37.292] [Prompt Server] web root: /home/comdoleger1/zen-flux-style-shape/web [2025-04-08 18:08:37.578] Traceback (most recent call last): File "/home/comdoleger1/zen-flux-style-shape/nodes.py", line 2037, in load_custom_node module_spec.loader.exec_module(module) File "", line 883, in exec_module File "", line 241, in _call_with_frames_removed File "/home/comdoleger1/zen-flux-style-shape/comfy_extras/nodes_audio.py", line 1, in import torchaudio File "/opt/conda/envs/fuzer/lib/python3.10/site-packages/torchaudio/__init__.py", line 2, in from . import _extension # noqa # usort: skip File "/opt/conda/envs/fuzer/lib/python3.10/site-packages/torchaudio/_extension/__init__.py", line 38, in _load_lib("libtorchaudio") File "/opt/conda/envs/fuzer/lib/python3.10/site-packages/torchaudio/_extension/utils.py", line 60, in _load_lib torch.ops.load_library(path) File "/opt/conda/envs/fuzer/lib/python3.10/site-packages/torch/_ops.py", line 1357, in load_library ctypes.CDLL(path) File "/opt/conda/envs/fuzer/lib/python3.10/ctypes/__init__.py", line 374, in __init__ self._handle = _dlopen(self._name, mode) OSError: /opt/conda/envs/fuzer/lib/python3.10/site-packages/torchaudio/lib/libtorchaudio.so: undefined symbol: _ZN2at4_ops9fft_irfft4callERKNS_6TensorESt8optionalIN3c106SymIntEElS5_INS6_17basic_string_viewIcEEE [2025-04-08 18:08:37.578] Cannot import /home/comdoleger1/zen-flux-style-shape/comfy_extras/nodes_audio.py module for custom nodes: /opt/conda/envs/fuzer/lib/python3.10/site-packages/torchaudio/lib/libtorchaudio.so: undefined symbol: _ZN2at4_ops9fft_irfft4callERKNS_6TensorESt8optionalIN3c106SymIntEElS5_INS6_17basic_string_viewIcEEE [2025-04-08 18:08:38.216] ------------------------------------------ [2025-04-08 18:08:38.216] Comfyroll Studio v1.76 :  175 Nodes Loaded [2025-04-08 18:08:38.216] ------------------------------------------ [2025-04-08 18:08:38.216] ** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md [2025-04-08 18:08:38.216] ** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki [2025-04-08 18:08:38.216] ------------------------------------------ [2025-04-08 18:08:38.220] Total VRAM 81038 MB, total RAM 171070 MB [2025-04-08 18:08:38.220] pytorch version: 2.6.0+cu124 [2025-04-08 18:08:38.220] Set vram state to: NORMAL_VRAM [2025-04-08 18:08:38.221] Device: cuda:0 NVIDIA A100-SXM4-80GB : native [2025-04-08 18:08:40.857] [comfy_mtb] | INFO -> loaded 81 nodes successfuly [2025-04-08 18:08:40.857] [comfy_mtb] | INFO -> Some nodes (9) could not be loaded. This can be ignored, but go to http://127.0.0.1:8188/mtb if you want more information. [2025-04-08 18:08:40.859] ### Loading: ComfyUI-Manager (V2.54) [2025-04-08 18:08:40.870] ### ComfyUI Revision: 33 on 'main' [96f0f3d8] | Released on '2024-12-19' [2025-04-08 18:08:40.889] [2025-04-08 18:08:40.889] [rgthree-comfy] Loaded 42 exciting nodes. 🎉 [2025-04-08 18:08:40.889] [2025-04-08 18:08:40.917] xFormers not available [2025-04-08 18:08:40.921] xFormers not available [2025-04-08 18:08:40.924] Import times for custom nodes: [2025-04-08 18:08:40.925] 0.0 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/websocket_image_save.py [2025-04-08 18:08:40.926] 0.0 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/ComfyUI-to-Python-Extension [2025-04-08 18:08:40.926] 0.0 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/ComfyUI-DepthAnythingV2 [2025-04-08 18:08:40.927] 0.0 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/ComfyUI-Manager [2025-04-08 18:08:40.928] 0.0 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/rgthree-comfy [2025-04-08 18:08:40.929] 0.0 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/ComfyUI_essentials [2025-04-08 18:08:40.929] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json [2025-04-08 18:08:40.930] 0.0 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/ComfyUI-KJNodes [2025-04-08 18:08:40.930] 0.1 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/ComfyUI-SaveAsScript [2025-04-08 18:08:40.930] 0.6 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/ComfyUI_Comfyroll_CustomNodes [2025-04-08 18:08:40.931] 2.6 seconds: /home/comdoleger1/zen-flux-style-shape/custom_nodes/comfy_mtb [2025-04-08 18:08:40.931] [2025-04-08 18:08:40.931] WARNING: some comfy_extras/ nodes did not import correctly. This may be because they are missing some dependencies. [2025-04-08 18:08:40.931] IMPORT FAILED: nodes_audio.py [2025-04-08 18:08:40.931] This issue might be caused by new missing dependencies added the last time you updated ComfyUI. [2025-04-08 18:08:40.931] Please do a: pip install -r requirements.txt [2025-04-08 18:08:40.931] [2025-04-08 18:08:40.937] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json [2025-04-08 18:08:40.968] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json [2025-04-08 18:08:41.010] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json [2025-04-08 18:08:41.067] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [2025-04-08 18:08:41.207] /opt/conda/envs/fuzer/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884 warnings.warn( [2025-04-08 18:08:42.630] clip missing: ['text_projection.weight'] [2025-04-08 18:08:42.890] Using pytorch attention in VAE [2025-04-08 18:08:42.892] Using pytorch attention in VAE [2025-04-08 18:08:43.101] model weight dtype torch.bfloat16, manual cast: None [2025-04-08 18:08:43.102] model_type FLUX [2025-04-08 18:08:48.130] Loading model from: /home/comdoleger1/zen-flux-style-shape/models/depthanything/depth_anything_v2_vitl_fp32.safetensors [2025-04-08 18:08:48.133] using MLP layer as FFN [2025-04-08 18:08:49.045] Requested to load AutoencodingEngine [2025-04-08 18:08:49.045] Requested to load FluxClipModel_ [2025-04-08 18:08:49.045] Requested to load Flux [2025-04-08 18:08:49.045] Requested to load CLIPVisionModelProjection [2025-04-08 18:08:49.046] Loading 4 new models [2025-04-08 18:08:49.108] loaded completely 0.0 159.87335777282715 True [2025-04-08 18:08:51.444] loaded completely 0.0 9319.23095703125 True [2025-04-08 18:08:57.903] loaded completely 0.0 22700.509887695312 True [2025-04-08 18:08:58.142] loaded completely 0.0 787.7150573730469 True [2025-04-08 18:08:58.502] * Running on local URL: http://127.0.0.1:7860 [2025-04-08 18:08:58.513] HTTP Request: GET http://127.0.0.1:7860/gradio_api/startup-events "HTTP/1.1 200 OK" [2025-04-08 18:08:58.531] HTTP Request: HEAD http://127.0.0.1:7860/ "HTTP/1.1 200 OK" [2025-04-08 18:08:58.885] HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" [2025-04-08 18:08:59.223] HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK" [2025-04-08 18:08:59.926] * Running on public URL: https://c39c69141482606010.gradio.live [2025-04-08 18:08:59.926] This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces) [2025-04-08 18:11:03.648] Requested to load ControlNetFlux [2025-04-08 18:11:03.649] Loading 1 new model [2025-04-08 18:11:04.044] loaded completely 0.0 1418.6997985839844 True [2025-04-08 18:12:37.732] Keyboard interruption in main thread... closing server. [2025-04-08 18:12:37.852] Killing tunnel 127.0.0.1:7860 <> https://c39c69141482606010.gradio.live