The dataset is made of anime screencaps.
I tried tagging all four outfits, which turned out pretty good.
I'm still pretty new to Illustrious LoRAs, so I just used the parameters i was using for PonyXL LoRAs.
An epoch with relatively good balance between likeliness to the original and overall quality.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.