A style LoRA for Anima (by extension its finetunes) by <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs">CircleStone Labs</a>. This LoRA was trained on a curated dataset of 108 Illustrations from <a rel="ugc" href="https://www.pixiv.net/en/users/17151277">mamimi</a>. All images were treated to remove text, any censoring and most symbols, then batch tagged with <a target="_blank" rel="ugc" href="https://huggingface.co/Mooshie/convnextv2_huge.dbv4-full">ConvNextV2 Huge Full</a> 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 M4MIMI. Also this was trained on my chef's kiss AMD 7900XT, (under Linux with <a target="_blank" rel="ugc" href="https://github.com/ostris/ai-toolkit/">Ostris's Ai-Toolkit</a>❤️)

MAMIMI-STYLE-ANIMA

Main Settings: 2000Steps, AdamW8bit, 4Batches, [768,1024], LR 5e-5, WeightDecay 1e-2, Rank32, Repeats 2 |Made to be bolder and more erratic than V0.1 This version is less stable but more creative/faithful|

Files with SHA256: 8807e7232b8fa42b98fea671594cd0fb24517a4420f3a25fb49c6d84c59d6a26