CivArchive
    nonco style DoRA (Illustrious-XL) - v8.1 (LoRA)
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    This model was trained using images from nonco. Trigger word nonco is optional, but it does make the style more pronounced.

    I really like nonco's style and anatomy. I was going to release this for pony initially, but then illustrious came out. If you still want the pony version, leave a comment.

    Changelog

    • v8: trained on 55 images, labelled with wd1.4 and manually cleaned

      • v8.1 is trained for less iterations, so it should be more flexible, however the artist style is less pronounced

      • v8.2 is trained for more iterations, and it reproduces the style better, but it can be less stable

      • v8.3 is almost the same training parameters as v8.2, but it is trained as a DoRA; it can reproduce the style quite well, have a lot of variety, and seems quite stable

    • v9: added 28 (upscaled) images from manga, labelled with wd1.4

    Description

    LoRA trained on 55 images with kohya_ss

    • optimizer - AdamW

    • lr - 3e-4

    • unet lr - 2e-4

    • text lr - 5-e4

    • lr scheduler - linear

    FAQ

    DoRA
    Illustrious

    Details

    Downloads
    29
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/16/2024
    Updated
    4/22/2026
    Deleted
    -

    Files

    noncoStyleDora_v81Lora.safetensors