Skip to content

ccharest93/Stable-Diffusion

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Stable-Diffusion

Cleaned up the code from Stable UnCLIP 2.1 removing a lot of the bells and whistle from the original to improve readability, Implemented stricter GPU memory management allowing me to run inpainting of 768x768 image on a 6GB GPU.

Usage: download the checkpoints for inpainting and put them in the checkpoints directory

python LatentDiffusionInpainting.py <path-to-checkpoint>

I'll be working on a docker container to run this on AWS, but the roadmap for when i come back includes:

  • Implementation of the other gradio functions
  • Allowing for swapping of modules and finetuning

let me know if you think other directions might be interesting

⭐ if you find useful so i know to release more tools in this direction

About

Stable diffusion implementation for GPU memory efficiency

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages