Gfpgan

🚀 See you again 😸

✨ **Highlights**
✅ [remove codeformer](https://github.com/TencentARC/GFPGAN/commit/bc5a5deb95a4a9653851177985d617af1b9bfa8b)

<p align="center">
<img src="https://raw.githubusercontent.com/TencentARC/GFPGAN/master/assets/gfpgan_logo.png" height=150>
</p>

✨ **Highlights**
✅[add restoreformer and codeformer inference codes](https://github.com/TencentARC/GFPGAN/commit/126c55c68d9edf96ecac575a277affc33ddb3770)
✅[update cog predict](https://github.com/TencentARC/GFPGAN/commit/3fd33abc47ba796c4ba9e37dbffa1d848fc10c03)

<p align="center">
<img src="https://raw.githubusercontent.com/TencentARC/GFPGAN/master/assets/gfpgan_logo.png" height=150>
</p>

🚀Have a nice day 😸

🐛 **Bug Fixes**
✅ [fix basicsr losses import](https://github.com/TencentARC/GFPGAN/commit/7d657f26b66c3e01a969d1598b41ce65c9883c55)

🌴 **Improvements**
✅ [update facelib; use seg to paste back](https://github.com/TencentARC/GFPGAN/commit/c7ccc098a7e3120eb666050e991ae111dcdadf34)
✅ [add device to GFPGANer for multiGPU support](https://github.com/TencentARC/GFPGAN/commit/bc3f0c4d91293fdadd0ecbcce3a18a7a93abe50a)

<p align="center">
<img src="https://raw.githubusercontent.com/TencentARC/GFPGAN/master/assets/gfpgan_logo.png" height=150>
</p>

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](https://www.google.com/search?q=4k+logo))
So I release a new version~

You can see it on [ReadMe](https://github.com/TencentARC/GFPGAN)

<p align="center">
<img src="https://raw.githubusercontent.com/TencentARC/GFPGAN/master/assets/gfpgan_logo.png" height=150>
</p>

Actually, this release note is copied from [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN), haha

See you again today 🐱

🚀 Have a nice day

✨ Highlights

- Add [V1.3 model](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth), which produces **more natural** restoration results, and better results on very low-quality / high-quality inputs. See more in [Model zoo](https://github.com/TencentARC/GFPGAN#european_castle-model-zoo), [Comparisons.md](https://github.com/TencentARC/GFPGAN/blob/master/Comparisons.md)
- Add the 'bilinear' arch, which is the original arch for the clean arch. So that we can fine-tune the models with the clean arch.
- Add [baseten.co demo](https://app.baseten.co/applications/Q04Lz0d/operator_views/8qZG6Bg) provided by https://github.com/TencentARC/GFPGAN/commit/c068e4d113ebbca1f624e4e90854d21601f9c2ef

This release also stores the following pre-trained models ;-)
- GFPGANv1.3.pth