CivArchive
    Preview 130929219
    Preview 130928585
    Preview 130928583
    Preview 130928584
    Preview 130928586
    Preview 130928752
    Preview 130929220
    Preview 130929224
    Preview 130929337
    Preview 130977713
    Preview 130977712

    Trained on images from haiz ai


    MOSS

    Near perfect recreation of the style, not much to say, this model learns extremely well.

    Lower strength if you want less effect.

    If you find the effect to be too small on out of distribution prompts, adding Minimalist flat illustration helps a lot

    Anima

    Strength 1.25 / 1.5 might give more stylized results.

    Description

    Training Settings: batch size 4, mixed res from 512px to 1216px, ~251 images per epoch, optimizer is SinkSGD_adv

    FAQ

    LORA
    Anima

    Details

    Downloads
    1,013
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/16/2026
    Updated
    11/20/2026
    Deleted
    -
    Trigger Words:
    @haiz ai,

    Files

    haizai_anima-base1_v1.safetensors

    Mirrors