Inspired by a recently posted Lora, I decided to make one that... suck at least a little bit less :D
Still isn't as good as I would hope, the poses it outputs aren't always the same, but I don't think I'll realistically be able to make something with 100% accuracy, at least not yet.
To work properly the picture should be a 1024x288, the example images have been made with Hires.fix.
Description
FAQ
Comments (2)
looks really cool! Hope you can improve it in the next version!
Can you tell me where did you get the dataset? I think I can make it a little bit more easy for a training model to understand
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.