Img2img - Githubissues

NickLucche / stable-diffusion-nvidia-docker

GPU-ready Dockerfile to run Stability.AI stable-diffusion model v2 with a simple web interface. Includes multi-GPUs support.

MIT License

359 stars 43 forks source link

Img2img #20

Closed NickLucche closed 1 year ago

NickLucche commented 1 year ago

Img2Img winter update!

text-guided image conditioned generation (img2img), either from simple sketch or uploaded image. No model reload required
img inpainting. Model reload required, can be done from UI!
newly refreshed UI! 3 input tabs, text-img2img-img inpainting

mchaker commented 1 year ago

Awesome! Thank you so much :)

NickLucche commented 1 year ago

Updated UI with image inpainting. I am planning to refactor this code a bit while including support for newer models in the next PRs. Some bugs with UI are still expected until I tidy things up, I will try to keep it very basic so that it can be more stable (aka it won't ever be as fancy as other projects).