!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 :)
Description
v1
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.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.