You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Looking for directions where to head with the following error that I'm getting all the sudden
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.1.0+cu121 with CUDA 1201 (you have 2.0.1+cu118)
Python 3.10.13 (you have 3.10.10)
Running the xformers building block produces the further error if ADetailer is turned on:
RuntimeError: Couldn't load custom C++ ops.
This can happen if your PyTorch and torchvision versions are incompatible, or if you had errors while compiling torchvision from source. For further information on the compatible versions, check https://github.com/pytorch/vision#installation for the compatibility matrix. Please check your PyTorch version with torch.version and your torchvision version with torchvision.version and verify if they are compatible, and if not please reinstall torchvision so that it matches your PyTorch install.
Any assistance on where I should be looking for help next is appreciated
The text was updated successfully, but these errors were encountered:
I also started recently getting this error out of the blue. The webui starts up normally, but runs into the error when trying to generate images. I tried running with --xformers but that didn't fix the error.
For what it's worth, I've been able to fix this by installing xformers through the terminal after everything else is installed (just run "pip install xformers"). But, this needs to be done for every new session.
Looking for directions where to head with the following error that I'm getting all the sudden
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.1.0+cu121 with CUDA 1201 (you have 2.0.1+cu118)
Python 3.10.13 (you have 3.10.10)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
Running the xformers building block produces the further error if ADetailer is turned on:
RuntimeError: Couldn't load custom C++ ops.
This can happen if your PyTorch and torchvision versions are incompatible, or if you had errors while compiling torchvision from source. For further information on the compatible versions, check https://github.com/pytorch/vision#installation for the compatibility matrix. Please check your PyTorch version with torch.version and your torchvision version with torchvision.version and verify if they are compatible, and if not please reinstall torchvision so that it matches your PyTorch install.
Any assistance on where I should be looking for help next is appreciated
The text was updated successfully, but these errors were encountered: