# Face recovery doesn't understand eye-glasses

**URL:** <https://community.topazlabs.com/t/face-recovery-doesnt-understand-eye-glasses/56663>\
**Category:** Bugs and Issues\
**Created:** [November 21, 2023, 9:01am UTC](https://community.topazlabs.com/t/face-recovery-doesnt-understand-eye-glasses/56663 "2023-11-21T09:01:03Z")\
**Posts on this page:** 1\
**Showing post:** 9

<div class="post-metadata">

**Author:** ![lhkjacky](https://community.topazlabs.com/user_avatar/community.topazlabs.com/lhkjacky/32/256798_2.png) [@lhkjacky](https://community.topazlabs.com/u/lhkjacky)\
**Post date:** [November 22, 2023, 11:16am UTC](https://community.topazlabs.com/t/face-recovery-doesnt-understand-eye-glasses/56663/9 "2023-11-22T11:16:48Z")

</div>

> [@nicholas.simpson](#):
>
> what AI program you used for that

It is free program from Github and I further enhance the eyes using stable diffusion.

For more detail about the program, you may refer to the post here

> [@V2.0.1 faces look like wax museum](https://community.topazlabs.com/t/v2-0-1-faces-look-like-wax-museum/52325/10):
>
> The “Others” images are upscaled using the latest AI upscaling algorithm called DiffBIR, developed by the Chinese Academy of Sciences and Shanghai AI Laboratory. They recently released their research paper in arXiv. DiffBIR utilizes stable diffusion and controlnet to upscale images and regenerate realistic details, including hair, skin texture, clothing texture, text, trees leaves, grasses and more. Based on my testing, their face recovery surpasses that of GPEN, GFPGAN, CodeFormer, and VQFR,…

---

_[View the full topic](https://community.topazlabs.com/t/face-recovery-doesnt-understand-eye-glasses/56663)._