V0.3 Important Notes: Trained with Danboru tags and Natural language, real pain in the ass to manually write/edit but, better prompt adherence. Bumped to 4000 Steps. I managed to work on this one fast (only trained 3 times to test), and got a huge step-up for my automated natural language pre-caption. We're SO BACK. <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f2b1a52b-6140-41a3-963b-c2d4e220d098/original=true/f2b1a52b-6140-41a3-963b-c2d4e220d098.jpeg" /> 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 84 Illustrations from <a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/37246244">Snegovski</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 SNEG0VSKI. 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>❤️)

SNEGOVSKI-SYTLE-ANIMA

Main Settings: 4000Steps, AdamW8bit, 1Batches, [768], LR 4e-5, WeightDecay 1e-2, Rank32, Repeats 2(TAG) and 2(CAPTION), No X Axis Flip [Trained with both Danbooru Tags and Natural Language. Tags weight 1.4, Caption Weight 0.6]

Files with SHA256: 830bddd52e373dd6ee67f06d4981d5828a3dc645b45795c159777f5c1432716a