Replies: 2 comments
-
Ok by adding the suggested "--skip-torch-cuda-test" to the "webui-user.bat" file I now get a few errors though the web ui does now open. return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled) And a few other errors in CMD while it opens the web ui, but doesn't work. Did I miss a step or what can I do at this point? |
Beta Was this translation helpful? Give feedback.
-
Try adding https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hello all,
I know the answer will be "AMD sucks" already, but I have a computer with a 6800M 12gb VRAM 64GB RAM and really expected to be able to run this.
After downloading and running the "webui-user.bat" file I got this result:
Traceback (most recent call last):
File "C:\Users\XXXXXXXX\OneDrive\Desktop\AI Image Models\stable-diffusion-webui\launch.py", line 48, in
main()
File "C:\Users\XXXXXXXX\OneDrive\Desktop\AI Image Models\stable-diffusion-webui\launch.py", line 39, in main
prepare_environment()
File "C:\Users\XXXXXXXX\OneDrive\Desktop\AI Image Models\stable-diffusion-webui\modules\launch_utils.py", line 356, in prepare_environment
raise RuntimeError(
RuntimeError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
Any help would be amazing. Super inexperienced with this type of stuff, but was able to get a lanuage model running on the same computer the other day so I thought it would be possible. Let me know if you have any suggestions or Ideas (or if you just know of the right Discord to join that might help)
Thanks!
Beta Was this translation helpful? Give feedback.
All reactions