divamgupta / divamgupta/diffusionbee-stable-diffusion-ui

Feature Request: Fix faces

Open
#249 0 comments 5 reactions 0 assignees View on GitHub
Dominant language
JavaScript
Stars
13.6k
Forks
727
PR merge metrics
No merged PRs in 30d

Description

Hi, I do not like to ask for features, I believe that I should do it by myself, but I am not yet acquitted building these technologies.

But I want to ask if it is possible to add an AI filter to fix faces.
I use https://huggingface.co/spaces/havas79/Real-ESRGAN_Demo (Face Enhancement using GFPGAN) and it works really well.

I even pass the same picture multiple times, for better improvements. An example:

Difussion Bee:
![e1f8d2fa-05d8-4794-b530-1daac1c31157](https://user-images.githubusercontent.com/2758345/197756622-edc01a41-e498-439c-805c-ebfa51aa02e5.jpeg).

First Face Enhancement:
![Unknown-5](https://user-images.githubusercontent.com/2758345/197756637-959e93ef-2d63-406d-aae5-ce10ff68cc6d.jpeg)

Second Face Enhancement (over the previous result):
![Unknown-6](https://user-images.githubusercontent.com/2758345/197756667-160ff798-9145-496a-8fb7-3c7cdc28aae8.jpeg)

It really makes wonders.

Thanks for the great job!!

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.