NOTES:
Some recommended tags are : feet, toes, blunt bangs, monolids, aegyo sal,monochrome background, ect...
A style LoRA for Anima (by extension its finetunes) by CircleStone Labs.
This LoRA was trained on a curated dataset of 56 Illustrations from Kusujinn. 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 KUSUJ1NN.
Also this was trained on my chef's kiss AMD 7900XT, (under Linux with Ostris's Ai-Toolkit❤️)
Description
Main Settings: 2000Steps, AdamW8bit, 4Batches, [768,1024], LR 5e-5, WeightDecay 1e-2, Rank32, Repeats 3