Open MarsEverythingTech opened 1 month ago
If your PC is Windows OS, have you checked https://github.com/Zheng-Chong/CatVTON/issues/8 ?
If your PC is Windows OS, have you checked #8 ?
Yes, I am on Windows 11, I also checked #8, but I am getting this error: LoadAutoMasker CatVTON AutoMasker LoadCatVTONPipeline Nodes that have failed to load will show as red on the graph.
What about https://github.com/Zheng-Chong/CatVTON/issues/7 , it seems you have similar situation?
What about #7 , it seems you have similar situation?
This is what I did:
1- Installed the repo from URL using Manager 2- Downloaded the Detectron2 & DensePose from Releases and extracted them in to ComfyUI\venv\Lib\site-packages 3- Downloaded the .json (workflow) then dragged it into ComfyUI. 4- After that, the error showed up.
Also, the post you mentioned #7, I already installed Visual Studio Build Tools, but that still didn't help.
2.Download ComfyUI-CatVTON.zip and unzip it in the custom_nodes folder under your ComfyUI project (clone from ComfyUI).
2.Download ComfyUI-CatVTON.zip and unzip it in the custom_nodes folder under your ComfyUI project (clone from ComfyUI).
Yes, I have already done that, but it didn't work
2.Download ComfyUI-CatVTON.zip and unzip it in the custom_nodes folder under your ComfyUI project (clone from ComfyUI).
Yes, I have already done that, but it didn't work
After that. have you restarted the ComfyUI?
2.Download ComfyUI-CatVTON.zip and unzip it in the custom_nodes folder under your ComfyUI project (clone from ComfyUI).
Yes, I have already done that, but it didn't work
After that. have you restarted the ComfyUI?
Yes I did.
I'm very sorry that we can't solve your problem, but we don't have a test machine running on WindowsOS and can't reproduce your problem, so we can't provide further help. I saw that you also raised the same problem in another repo Comfyui-catvton expecially for WindowOS, maybe it can be solved there.
I'm very sorry that we can't solve your problem, but we don't have a test machine running on WindowsOS and can't reproduce your problem, so we can't provide further help. I saw that you also raised the same problem in another repo Comfyui-catvton expecially for WindowOS, maybe it can be solved there.
How about installing it locally, I am just having trouble with the last step and is giving me this error:
note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for detectron2 Running setup.py clean for detectron2 Successfully built detectron2-densepose Failed to build detectron2 ERROR: Could not build wheels for detectron2, which is required to install pyproject.toml-based projects
I'm very sorry that we can't solve your problem, but we don't have a test machine running on WindowsOS and can't reproduce your problem, so we can't provide further help. I saw that you also raised the same problem in another repo Comfyui-catvton expecially for WindowOS, maybe it can be solved there.
How about installing it locally, I am just having trouble with the last step and is giving me this error:
note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for detectron2 Running setup.py clean for detectron2 Successfully built detectron2-densepose Failed to build detectron2 ERROR: Could not build wheels for detectron2, which is required to install pyproject.toml-based projects
Another issue in detectron2 repo provides a solution, maybe you can try it. https://github.com/facebookresearch/detectron2/issues/5008#issuecomment-1787796388
I'm very sorry that we can't solve your problem, but we don't have a test machine running on WindowsOS and can't reproduce your problem, so we can't provide further help. I saw that you also raised the same problem in another repo Comfyui-catvton expecially for WindowOS, maybe it can be solved there.
How about installing it locally, I am just having trouble with the last step and is giving me this error: note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for detectron2 Running setup.py clean for detectron2 Successfully built detectron2-densepose Failed to build detectron2 ERROR: Could not build wheels for detectron2, which is required to install pyproject.toml-based projects
Another issue in detectron2 repo provides a solution, maybe you can try it. facebookresearch/detectron2#5008 (comment)
Would using a Docker help?
is pip install git+https://github.com/facebookresearch/detectron2.git@v0.6#subdirectory=projects/DensePose
the command you use?
https://github.com/Zheng-Chong/CatVTON/issues/5 reported the installment error of detectron2 in Win.
is
pip install git+https://github.com/facebookresearch/detectron2.git@v0.6#subdirectory=projects/DensePose
the command you use?5 reported the installment error of detectron2 in Win.
Yes, I followed the step and got them installed. However, when running: python app.py --output_dir="resource/demo/output" --mixed_precision="bf16" --allow_tf32
I get the following error:
No CUDA runtime is found, using CUDA_HOME='C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin\'
C:\Users\miniconda3\envs\catvton\lib\site-packages\torch\utils\cpp_extension.py:383: UserWarning: Error checking compiler version for cl: [WinError 2] The system cannot find the file specified
warnings.warn(f'Error checking compiler version for {compiler}: {error}')
Traceback (most recent call last):
File "C:\CatVTON\app.py", line 12, in
It looks like your torch and cuda versions conflict, maybe you can google the specific error message
It looks like your torch and cuda versions conflict, maybe you can google the specific error message
Could you please help me fix it?
It looks like your torch and cuda versions conflict, maybe you can google the specific error message
Ok now I am getting this error:
C:\Users\miniconda3\envs\catvton\lib\site-packages\torch\utils\cpp_extension.py:380: UserWarning: Error checking compiler version for cl: [WinError 2] The system cannot find the file specified
warnings.warn(f'Error checking compiler version for {compiler}: {error}')
C:\Users\miniconda3\envs\catvton\lib\site-packages\torch\utils\cpp_extension.py:1965: 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(
INFO: Could not find files for the given pattern(s).
Traceback (most recent call last):
File "C:\CatVTON\app.py", line 12, in
I'm sorry, but the environment setup is quite complex. It involves not only the operating system but also graphics card drivers and dependencies of other packages. I find it difficult to provide specific help to fix the bug for you.
I will keep this issue open to see if anyone else encounters a similar problem.
I'm sorry, but the environment setup is quite complex. It involves not only the operating system but also graphics card drivers and dependencies of other packages. I find it difficult to provide specific help to fix the bug for you.
I will keep this issue open to see if anyone else encounters a similar problem.
Hello, I have fixed that error by installing other packages for VS Build Tools, however, I am having this issue: \miniconda3\envs\catvton\lib\site-packages\torch\utils\cpp_extension.py:1965: 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'].
Then I did: set TORCH_CUDA_ARCH_LIST="8.6" but returned with another error: File "C:\Users\miniconda3\envs\catvton\lib\site-packages\torch\utils\cpp_extension.py", line 1998, in _get_cuda_arch_flags raise ValueError(f"Unknown CUDA arch ({arch}) or GPU not supported") ValueError: Unknown CUDA arch ("8.6") or GPU not supported
I was able to get it working on windows but had to do a few adjustments in order to successfully build the modules
I was able to get it working on windows but had to do a few adjustments in order to successfully build the modules
Amazing! Could you please provide me the steps on how you made it work?
Thanks in advance
failed on win11 but with error:
Ninja is required to load C++ extensions
but in fact
pip install ninja
works
For the "where cl" error, Starting ComfyUI using “x64 Native Tools Command Prompt for VS 2022”,Do not using original cmd/powershell. That's maybe the problem of the VC env settings in WindowsOS.
Hello,
I was trying to install the repo locally on my PC, however, I was unable to perform the last step: pip install git+https://github.com/facebookresearch/detectron2@main#subdirectory=projects/DensePose as it is giving me an error in red: error: could not build wheels for detectron2, which is required to install pyproject.toml-based projects I've been told to install VS Build Tools but that didn't help.
Thanks in advance