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

Add AuraSR/GigaGAN upscaler #298

Open
isidentical opened this issue Jul 15, 2024 · 2 comments
Open

Add AuraSR/GigaGAN upscaler #298

isidentical opened this issue Jul 15, 2024 · 2 comments
Labels
Arch request Request to add support for an architecture

Comments

@isidentical
Copy link

AuraSR is a new open source upscaler for synthetically generated images specifically (doesn't do restoration etc for now, but v2 might do it) that is based on lucidrains/GigaGAN. Might make sense to add it, there is a super simple / self-contained pytorch implementation here: https://github.com/fal-ai/aura-sr/blob/main/aura_sr.py

@RunDevelopment RunDevelopment added the Arch request Request to add support for an architecture label Jul 16, 2024
@zelenooki87
Copy link

They updated model to v2
https://huggingface.co/fal/AuraSR-v2/tree/main
It is not bad as before :)
Could oyu add support?

@zelenooki87
Copy link

@isidentical
With a little difficulty, I have successfully converted the AuraSR v2 model (an open-source alternative to GigaGAN). Version v2 is quite decent, unlike the first version which produced many artifacts. The fp32 model would have exceeded 2GB in size and wouldn't fit into a single file. So, I created an fp16 version.
https://mega.nz/folder/8kA2mKzZ#LWahzxk-447JaRSx3Xp_OQ

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Arch request Request to add support for an architecture
Projects
None yet
Development

No branches or pull requests

3 participants