!WARNING OVERTRAINED! 250 images at 25000 steps. You need to lower the strength because at strength 1 it's way too strong and ruins the style.
LoRA trained on Slugbox NSFW works. Cleaned aesthetic dataset by me.
Insert into prompt like any other LoRA.
Strength recommended: 0.1-0.8 work ok. It really breaks down after 0.8. Sweetspot 0.3-0.6
Trained on my anything v4.5 based mix but seems to work on most popular anime models and mixes just as well.
If you feel like supporting my art democratization efforts you can donate here -> https://ko-fi.com/atlasdiffusion Any donations are appreciated :)
v1
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.