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
Resized lora to dim 96
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