So, I tried to make a multipurpose lora with images of various boots and in the end it was ok enough, but I was curious to see how the lora I made would stack up against a wildcard which ended up being more dynamic with generation and saved me from training and tagging hundreds of images, which I do plan to do just for fun and see what's the difference.
Anyhow, wildcard is a good start, works much better with flux as prompts the wildcard manages are more suited to it, there's still a bit to do and test for v2 as well as making it work at least as well for Pony.
Description
Good starting point, still need to define a few things and add stuff, which I'll won't be able to do until 2025.
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.