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

Is it possible to use the cpu for sampling? #20

Closed
alienhd opened this issue Aug 15, 2022 · 4 comments
Closed

Is it possible to use the cpu for sampling? #20

alienhd opened this issue Aug 15, 2022 · 4 comments

Comments

@alienhd
Copy link

alienhd commented Aug 15, 2022

Wanted to try sampling on cpu but can't get it to work. Are there any solutions for this problem?

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0!

@jamesthesnake
Copy link

i don't think so

@leszekhanusz
Copy link

You could use export CUDA_VISIBLE_DEVICES="" so that cuda does not see your gpu, but you would probably have an other error.

See also latent-diffusion PR #123

@alienhd
Copy link
Author

alienhd commented Aug 18, 2022

@leszekhanusz Thanks for your help but can i ask you where you put the export CUDA_VISIBLE_DEVICES="" argument?

@leszekhanusz
Copy link

@leszekhanusz Thanks for your help but can i ask you where you put the export CUDA_VISIBLE_DEVICES="" argument?

In the bash console, before running the program, assuming you are on Linux. It is simply setting an environment variable.

enzymezoo-code pushed a commit to enzymezoo-code/stable-diffusion that referenced this issue Aug 27, 2022
File naming change that matches v0.0 but 5 digits as per discord discussions
colemickens pushed a commit to colemickens/stable-diffusion that referenced this issue Sep 15, 2022
🔥 🔥 Workaround for Gradio server hanging on keyboard interrupt 🔥 🔥  🥇
@alienhd alienhd closed this as completed Aug 4, 2023
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

3 participants