V0.2 Important Notes: PSA: Not really good at dark images, so either turn down or load a light dark LoRA. Also, pretty strong seed variance. Trained with Danboru tags and Natural language, real pain in the ass to manually write/edit but, better prompt adherence. Bumped to 4000 Steps. Wholesome LoRA for everyone, and especially girl kissers <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f8bac017-320d-4f9c-b33b-e48dfb4380a2/original=true/f8bac017-320d-4f9c-b33b-e48dfb4380a2.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 74 Illustrations from <a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/26057869">R-E-L-O-A-D</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 R3LOAD. 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>❤️)

RELOAD-STYLE-ANIMA

Main Settings: 4000Steps, AdamW8bit, 1Batches, [768,1024], LR 4e-5, WeightDecay 1e-2, Rank32, Repeats 3(TAG) and 3(CAPTION), No X Axis Flip [Trained with both Danbooru Tags and Natural Language. Tags weight 1.4, Caption Weight 0.6]

Files with SHA256: 83a46a1d041e68c38ce735104901d467a8545728d0602514691f1cf54ddfd342