GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
🚀Have a nice day 😸
🐛 Bug Fixes ✅ fix basicsr losses import
🌴 Improvements ✅ update facelib; use seg to paste back ✅ add device to GFPGANer for multiGPU support
Have a nice day 😸 and happy everyday 😃
I am happy to add a simple logo to GFPGAN 😋 (designed by myself! and inspired by the 4K logo) So I release a new version~
You can see it on ReadMe
Actually, this release note is copied from Real-ESRGAN, haha
See you again today 🐱
V1.3.0 has a lost code file, causing an import error.
We have fixed it in this version. 😃
🚀 Have a nice day
✨ Highlights
This release also stores the following pre-trained models ;-)
✅ We provide a clean version of GFPGAN, which does not require CUDA extensions. ✅ We provide an updated model without colorizing faces.
This release is mainly for storing pre-trained models, etc.