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

GPU compatibility #157

Open
im-pain opened this issue Sep 17, 2022 · 12 comments
Open

GPU compatibility #157

im-pain opened this issue Sep 17, 2022 · 12 comments
Assignees
Labels
enhancement New feature or request

Comments

@im-pain
Copy link

im-pain commented Sep 17, 2022

Hi, there is a way to use GPU instead CPU? waifuxl is the best anime upscaler i found, but it takes too much time in cpu in comparison to what cuda can do with realesrgan, ty for this marvelous tool!

@haydn-jones
Copy link
Member

Yes we can certainly support that, but likely not on the web version. ONNXRuntime Web's support for GPU's isn't great. I can write a python script using PyTorch that will be CUDA accelerated (you will need to run this locally on your own machine of course). Would that be sufficient?

@haydn-jones haydn-jones added the enhancement New feature or request label Sep 17, 2022
@haydn-jones haydn-jones self-assigned this Sep 17, 2022
@haydn-jones haydn-jones pinned this issue Sep 17, 2022
@im-pain
Copy link
Author

im-pain commented Sep 17, 2022

yes, thats perfect!
(also if you can add some instructions of requirements or examples of usage it would be great, thx!)

@haydn-jones
Copy link
Member

yes, thats perfect!

Great. I'll jot down some features I'll consider adding:

  • Command line configuration
  • Single image input support
  • Support input folder of images (perhaps recursive)
  • GIFs
  • Videos (stretch goal, will of course be slow)

Anything else you would like?

@im-pain
Copy link
Author

im-pain commented Sep 17, 2022

i think that cover all my possible usages 😄

@haydn-jones
Copy link
Member

Just bumping this to let you know I'm still working on this. Really just need to get the CLI set up and stuff, inference is done.

@im-pain
Copy link
Author

im-pain commented Nov 10, 2022

bumping here just to say im still hyped for this update!🦇

@haydn-jones
Copy link
Member

We'll get this out after we finish the website rewrite/redesign (you can get a sneak peek here https://de-spaghetti.waifuxl.pages.dev/). We're pretty close!

@im-pain
Copy link
Author

im-pain commented Nov 11, 2022

Okok, i'll keep waiting to the new rewrite(btw the sneak peek crashed my windows☠️)

@github-actions
Copy link

Stale issue message

@raziel2001au
Copy link

Just wanted to add that I'm also looking forward to the command line version. Ideally I'd like to be able to run it against image sequences, like a directory of PNGs so you can do entire video sequences.

@haydn-jones
Copy link
Member

This stupid bot keeps closing this issue. I'll get it done. Thanks for the support everyone

@haydn-jones
Copy link
Member

This will be addressed when we do 2.0. Pinky promise

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

No branches or pull requests

3 participants