Very much a WIP. I'm still learning about making loras.
This model is over-trained. It'll only give the same few images over and over again unless you turn the weight down a lot. .4-.6 tends to work. I'm really just putting it up here as an easy way to share with a few people, so sorry for the lack of details.
It's only really gonna work with women and side views.
Description
This version includes different angles. The previous one only really worked with side views. It doesn't do well with txt2img, but img2img works great.
This was made using the CivitAI trainer.
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.