Attempt at SDXL LoRA training, feel free to provide feedback.
Best works with tags
aogami,lineart,monochromeWithout monochrome,lineart provides you with nice stylized thick lines and characters.
For man of culture, furry tag works too, you know that already
I've uploaded resized version of 23 and 12 loras, they a bit different and have different strengths so it makes sense to try both
Description
Trained with fresh kohya code and bugfixes
FAQ
Comments (6)
Interesting interesting, hopefully will get better and smaller, Aogami have some very cool sketches.
can you introduce witch tool you use to train this lora? or give me a github link?
Any idea about LoRA size? You use higher values for information that should be (above 64), or it take so much space itself ?
i dont know why everyone is posting such big loras, there is no point in posting such a big size. do several size loras and compare them before posting more than half a gig of a lora
Many thanks, it’s a great Lora
This should be run-able on Civit
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.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.