V0.2 Important Notes:
PSA: This version (0.2) has a problem with lips and thick lips tags. I legit don't know why and already spent two weeks on this model, went through 7 iterations, that's 16Hours in training alone.

Trained with Danboru tags and Natural language, real pain in the ass to manually write/edit but, better prompt adherence.
Bumped to 3000 Steps.
Some recommended tags are : hatching (texture), linear hatching, plump, thick thighs, ect...

This one took forever and was hell to port to V0.2 natural language...


A style LoRA for Anima (by extension its finetunes) by CircleStone Labs.

This LoRA was trained on a curated dataset of 69(nice) Illustrations from Shrimp Cake. All images were treated to remove text, any censoring and most symbols, then batch tagged with ConvNextV2 Huge Full and manually tagged for fixing/adding tags.

This Lora is best used at 1.0 strength, imo. Trigger word is very optional, but hey, its SHR1MPCAKE.
Also this was trained on my chef's kiss AMD 7900XT, (under Linux with Ostris's Ai-Toolkit❤️)