๐Ÿš€ Want to run this model with an API? Get started

sczhou/codeformer

Public
Robust face restoration algorithm for old photos / AI-generated faces
4.3M runs

Run time and cost

Predictions run on Nvidia T4 GPU hardware. Predictions typically complete within 9 seconds.

Towards Robust Blind Face Restoration with Codebook Lookup Transformer (NeurIPS 2022)
Paper | Project Page | Video

visitors

Note that this web demo is for research purposes! If you want to use our CodeFormer for permanent free, you can run the [Github Code] locally or try out [Colab Demo] instead.


 
โ˜•๏ธ CodeFormer is a robust face restoration algorithm for old photos or AI-generated faces.
๐Ÿš€ Try CodeFormer for improved stable-diffusion generation!

If CodeFormer is helpful, please help to โญ the [Github Repo]. Thanks!

GitHub Stars

๐Ÿ“‹ License
This project is licensed under S-Lab License 1.0. Redistribution and use for non-commercial purposes should follow this license.

๐Ÿ“ Citation
If our work is useful for your research, please consider citing:

@inproceedings{zhou2022codeformer,
    author = {Zhou, Shangchen and Chan, Kelvin C.K. and Li, Chongyi and Loy, Chen Change},
    title = {Towards Robust Blind Face Restoration with Codebook Lookup TransFormer},
    booktitle = {NeurIPS},
    year = {2022}
}