CivArchive
    KUSUJINN-STYLE-ANIMA - V0.1
    NSFW
    Preview 139069984
    Preview 139069983
    Preview 139069987
    Preview 139069988
    Preview 139070006
    Preview 139070008

    V0.3 Important Notes:
    PSA: For Kusujinn's OC Twins use tags like: monolids, blunt bangs, asian, lips, nose, monochrome background.
    Trained with Danboru tags and Natural language, pain in the ass to manually write/edit but holly smokes, WAY better prompt adherence.
    Bumped to 4000 Steps with lower LR.

    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

    FAQ

    LORA
    Anima

    Details

    Downloads
    117
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/8/2026
    Updated
    10/6/2026
    Deleted
    -

    Files

    KUSUJ1NN-SYTLE-ANIMA-V0.1.safetensors

    Mirrors