I feel like there needs to be a model that fixes faces to clean this up. Humans ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		ALittleLight on Aug 26, 2022 \| parent \| context \| favorite \| on: Search over 5M+ Stable Diffusion images and prompt... I feel like there needs to be a model that fixes faces to clean this up. Humans are so attuned to faces that I can imagine it would take a specialized model to render convincing faces. Maybe there could be a layer to identify and occlude existing pseudo-faces generated by Stable Diffusion and another model to populate the occlusion.

meowface on Aug 26, 2022 | [–]

Many are doing exactly this with Stable Diffusion + GFPGAN (https://github.com/TencentARC/GFPGAN) as a post-processing model.

thomashop on Aug 26, 2022 | [–]

This is already done e.g. in Majesty Diffusion. You run another amount of iterations using a face Restauration GAN

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact