Images is generated on SDXL Lightning 4 steps. You should try it. Most "finetuned" models are just a joke.
1.0 Lightning trained on same dataset but on Dream Diffusion LIGHTNING XL & SD. Unfortunately, it does not give any positive effects with lightning models but give an amazing additional effects with regular SDXL.
It reduces/completely solves the problem of deformed eyes.
Recommended strength 0.5-0.7
Good for merging.
trained on close-up photographs of babies, children, men and women, as well as collages made from these photographs. The collages were needed to teach it how to deal with small faces. And it's works.
Description
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.