Open v4r4rth opened 3 days ago
It is weird that I have fixed this issue last week. Could you try the latest code of this repo? Or if still not working, the manual fix is: go to ComfyUI folder, and edit execution.py by text editor, find keyword with torch.inference_mode(), change it to torch.inference_mode(False)
I added the False flag and didn't get any errors. ComfyUI did crash though with a device segmentation fault... I am running this on an A40 server and the ComfyUI-3D-Pack is running just fine on it's own.
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-06-27 11:26:31.853999
** Platform: Linux
** Python version: 3.11.9 (main, Apr 19 2024, 16:48:06) [GCC 11.2.0]
** Python executable: /home/sid/.conda/envs/comfyui/bin/python
** Log path: /home/sid/ComfyUI/comfyui.log
Prestartup times for custom nodes:
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Easy-Use
0.8 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Manager
Total VRAM 48887 MB, total RAM 92515 MB
pytorch version: 2.3.1+cu121
xformers version: 0.0.16
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA A40-48Q : native
Using xformers cross attention
Warn!: xFormers is available (Attention)
Warn!: /home/sid/.conda/envs/comfyui/lib/python3.11/site-packages/torch/utils/cpp_extension.py:1967: UserWarning: TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards are included for compilation.
If this is not desired, please set os.environ['TORCH_CUDA_ARCH_LIST'].
warnings.warn(
### [START] ComfyUI AlekPet Nodes ###
Node -> ExtrasNode [Loading]
Node -> ArgosTranslateNode [Loading]
Node -> GoogleTranslateNode [Loading]
Node -> DeepTranslatorNode [Loading]
Node -> PainterNode [Loading]
Node -> PoseNode [Loading]
### [END] ComfyUI AlekPet Nodes ###
Total VRAM 48887 MB, total RAM 92515 MB
pytorch version: 2.3.1+cu121
xformers version: 0.0.16
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA A40-48Q : native
Warn!: /home/sid/ComfyUI/custom_nodes/comfyui_controlnet_aux/node_wrappers/dwpose.py:26: UserWarning: DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly
warnings.warn("DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly")
Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success!
Note: NumExpr detected 24 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 16.
NumExpr defaulting to 16 threads.
PyTorch version 2.3.1+cu121 available.
JAX version 0.4.29 available.
Warning! extra parameter in cli is not verified, may cause erros.
Loading pipeline components...: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:00<00:00, 128.21it/s]
You have disabled the safety checker for <class 'custum_3d_diffusion.custum_pipeline.unifield_pipeline_img2mvimg.StableDiffusionImage2MVCustomPipeline'> by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .
Warning! extra parameter in cli is not verified, may cause erros.
Warn!: /home/sid/.conda/envs/comfyui/lib/python3.11/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
warnings.warn(
Loading pipeline components...: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:00<00:00, 1711.54it/s]
You have disabled the safety checker for <class 'custum_3d_diffusion.custum_pipeline.unifield_pipeline_img2img.StableDiffusionImageCustomPipeline'> by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .
Comfy-Easy-Use v1.1.9: Loaded
/home/sid/ComfyUI
############################################
/home/sid/ComfyUI/custom_nodes/ComfyUI-NAI-styler/CSV
############################################
[]
############################################
A new version of Albumentations is available: 1.4.10 (you have 1.4.8). Upgrade using: pip install --upgrade albumentations
[comfy_mtb] | INFO -> loaded 77 nodes successfuly
[comfy_mtb] | INFO -> Some nodes (2) could not be loaded. This can be ignored, but go to http://127.0.0.1:7874/mtb if you want more information.
### Loading: ComfyUI-Manager (V2.42)
### ComfyUI Revision: 2284 [69d710e4] | Released on '2024-06-25'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `/home/sid/ComfyUI/custom_nodes/was-node-suite-comfyui/was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 216 nodes successfully.
"Art is the language of the heart and the window to the soul." - Unknown
!!!Hallo path was added to /home/sid/.conda/envs/comfyui/lib/python3.11/site-packages/Hallo.pth
if meet No module named 'hallo' error,please restart comfyui
Hallo use cache models,make sure your 'pretrained_models' complete
/home/sid/ComfyUI/custom_nodes/ComfyUI-Hallo/pretrained_models
[Allor]: 0 nodes were overridden.
[Allor]: 12 modules were enabled.
[Allor]: 98 nodes were loaded.
--------------
*ComfyUI_Jags_VectorMagic- nodes_loaded*
--------------
Jake Upgrade Nodes: 123 Nodes Loaded
------------------------------------------
Comfyroll Studio v1.76 : 175 Nodes Loaded
------------------------------------------
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
------------------------------------------
### Loading: ComfyUI-Impact-Pack (V5.18.1)
### Loading: ComfyUI-Impact-Pack (Subpack: V0.6)
[Impact Pack] Wildcards loading done.
Import times for custom nodes:
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Dream-Interpreter
0.0 seconds: /home/sid/ComfyUI/custom_nodes/websocket_image_save.py
0.0 seconds: /home/sid/ComfyUI/custom_nodes/cg-use-everywhere
0.0 seconds: /home/sid/ComfyUI/custom_nodes/comfyui_controlnet_aux
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Universal-Styler
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-HQ-Image-Save
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI_IPAdapter_plus
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Custom-Scripts
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI_densediffusion
0.0 seconds: /home/sid/ComfyUI/custom_nodes/Comfy_KepListStuff
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-IC-Light
0.0 seconds: /home/sid/ComfyUI/custom_nodes/comfyui-inpaint-nodes
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI_essentials
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Allor
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Advanced-ControlNet
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-JakeUpgrade
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-KJNodes
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI_Comfyroll_CustomNodes
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Impact-Pack
0.0 seconds: /home/sid/ComfyUI/custom_nodes/efficiency-nodes-comfyui
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Easy-Use
0.0 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Manager
0.1 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI_Jags_VectorMagic
0.1 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite
0.1 seconds: /home/sid/ComfyUI/custom_nodes/comfyui_segment_anything
0.2 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI_omost
0.3 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Hallo
1.0 seconds: /home/sid/ComfyUI/custom_nodes/comfy_mtb
1.4 seconds: /home/sid/ComfyUI/custom_nodes/was-node-suite-comfyui
3.3 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-3D-Pack
7.2 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI_Custom_Nodes_AlekPet
20.4 seconds: /home/sid/ComfyUI/custom_nodes/ComfyUI-Unique3D
Starting server
To see the GUI go to: http://127.0.0.1:7874
FETCH DATA from: /home/sid/ComfyUI/custom_nodes/ComfyUI-Manager/extension-node-map.json [DONE]
Error. No naistyles.csv found. Put your naistyles.csv in the custom_nodes/ComfyUI_NAI-mod/CSV directory of ComfyUI. Then press "Refresh".
Your current root directory is: /home/sid/ComfyUI
Error. No naistyles.csv found. Put your naistyles.csv in the custom_nodes/ComfyUI_NAI-mod/CSV directory of ComfyUI. Then press "Refresh".
Your current root directory is: /home/sid/ComfyUI
Error. No naistyles.csv found. Put your naistyles.csv in the custom_nodes/ComfyUI_NAI-mod/CSV directory of ComfyUI. Then press "Refresh".
Your current root directory is: /home/sid/ComfyUI
got prompt
Warn!: /home/sid/.conda/envs/comfyui/lib/python3.11/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
warnings.warn(
Loading pipeline components...: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:01<00:00, 5.63it/s]
Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference.
Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference.
Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference.
Loading pipeline components...: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 5388.83it/s]
RGB image not RGBA! still remove bg!
0%| | 0/30 [00:00<?, ?it/s]Warning! condition_latents is not None, but self_attn_ref is not enabled! This warning will only be raised once.
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 30/30 [00:01<00:00, 18.48it/s]
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:02<00:00, 4.19it/s]
Warn!: /home/sid/.conda/envs/comfyui/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py:69: UserWarning: Specified provider 'TensorrtExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider'
warnings.warn(
Warn!: /home/sid/.conda/envs/comfyui/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py:69: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider'
warnings.warn(
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 30/30 [00:09<00:00, 3.32it/s]
0%| | 0/200 [00:00<?, ?it/s]./start.sh: line 3: 194685 Segmentation fault python main.py --port 7874 --disable-cuda-malloc
hi, in fact while I tested this repo on Ubuntu with python 3.11 before, I encountered the same issue as yours, to be honest, I have no idea how to fix it, at that time, I changed my python from 3.11 to 3.10, and everything works well.
this python 3.11 issue only happens on Linux, as my test, Windows would not have this one, so my suggestion for this is, create a new conda env with 3.10, this is what we can do for now.
Getting this in the ComfyUI GUI for the error, please suggest what to do to be able to run the custom nodes
I am using the example workflow provided in this project
CLI log: