nateraw / stable-diffusion-videos

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
Apache License 2.0
4.42k stars 421 forks source link

Add support for face restoration on each frame during generation. #103

Open ZeroCool940711 opened 1 year ago

ZeroCool940711 commented 1 year ago

Just like the upsample option but for face restoration using something like GFPGAN, RestoreFormer or similar models, this would allow us to just pass an argument to the walk function to fix faces instead of having to do it manually during the callback or as a post-processing step.