Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Torch is not able to use GPU #38

Open
xyiphk opened this issue Apr 8, 2024 · 4 comments
Open

Torch is not able to use GPU #38

xyiphk opened this issue Apr 8, 2024 · 4 comments

Comments

@xyiphk
Copy link

xyiphk commented Apr 8, 2024

After I add this sd-webui-riffusion to SD webui, it said "Torch is not able to use GPU" and I cannot start the SD webui or I don't use GPU.
The big issue is that although I remove the sd-webui-riffusion from my SD webui, it cannot get back that it also said "Torch is not able to use GPU" or I don't use GPU.
CPU: AMD Ryzen 7 5800H with Radeon Graphics
GPU: RTX 3060 Laptop + AMD Radeon Graphics

@telos954
Copy link

Just posting that I'm having the same issue, and even after removing all the files I can find associated with it, I can not launch the webui.

CPU: AMD Ryzen 5 3600x
GPU: EVGA GeForce RTX 3070 Ti FTW3 Ultra

@jacob-willden
Copy link

jacob-willden commented Jul 3, 2024

I am also facing the same issue after adding sd-webui-riffusion to the Stable Diffusion Web UI.

venv "C:\Users\true3dnow\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.9.4
Commit hash: feee37d75f1b168768014e4634dcb156ee649c05
Traceback (most recent call last):
  File "C:\Users\true3dnow\stable-diffusion-webui\launch.py", line 48, in <module>
    main()
  File "C:\Users\true3dnow\stable-diffusion-webui\launch.py", line 39, in main
    prepare_environment()
  File "C:\Users\true3dnow\stable-diffusion-webui\modules\launch_utils.py", line 386, 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
Press any key to continue . . .

Steps to reproduce:

  1. Install and run stable-diffusion-webui (via the Automatic Installation on Windows section).
  2. Check that you can generate images with any model.
  3. Install sd-webui-riffusion as instructed, including installing ffmpeg and cloning the repo into the extensions folder.
  4. Close and re-run the Stable Diffusion Web UI via webui-user.bat.
  5. Notice that the "Torch is not able to use GPU" error now appears and trying to generate any images (once the Web UI loads) fails. It's worth noting that removing the extension does not fix the issues.
  6. Delete the Web UI and reinstall it without the extension.
  7. Run the Web UI once more and notice that generating images works again.

It's worth noting that I've tried restarting my computer after installing sd-webui-riffusion and running it with Stable Diffusion, and then tried running it again, with the same result.

My computer's stats:

  • Operating System: Windows 10
  • CPU: Intel(R) Core(TM) i9-9900K CPU @ 3.60GHz, 3600 Mhz, 8 Cores, 16 Logical Processors
  • GPU: NVIDIA GeForce RTX 2080 Ti

I'm happy to share any other information needed to troubleshoot this.

@4aiman
Copy link

4aiman commented Sep 8, 2024

Same here. Windows 11, Ryzen 3600, RTX4070.
Riffusion plugin breaks torch's ability to utilize CUDA

@jacob-willden
Copy link

jacob-willden commented Oct 16, 2024

Just to let everyone know, I found another repository that allows for self-hosting Riffusion, tts-generation-webui. I'm able to install it alongside stable-diffusion-webui and use both (not necessary if you only want to generate audio though).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants