CivArchive
    Tsuda Nanafushi Style - v1.0
    NSFW
    Preview 1790055
    Preview 1790104
    Preview 1790061
    Preview 1790065
    Preview 1790059
    Preview 1790064
    Preview 1790060
    Preview 1790067
    Preview 1790066
    Preview 1790063
    Preview 1790062
    Preview 1790068
    Preview 1790070
    Preview 1790069
    Preview 1790160

    A colorful drawing style LoRA. This is the LyCORIS version of the previously released LoRA. While trained on the same dataset it should produce a higher quality outputs while being more flexible prompting.

    How to use
    Prompt as usual, dataset contains a wide mix of females mainly biased towards fit, curvy, busty characters with some animal girls sprinkled in.
    For users of AOM2 or other models with photorealism in it you'll likely get better results adding "3D" and/or "realistic" in negatives. Alternatively you can do the opposite if you want to give a realistic model more strongthicc women.
    DIMM and DPM++ 2M Karras will recreate the drawing style closer while Euler A gives a more "clean" look.

    Misc
    Dataset of 370 all manually cleaned and processed trained at 512 resolution on NAI.
    All images are untouched txt2img upscaled, no inpainting or helper embeddings used for quality transparence, e.g. - things should look even better if you do.
    The training was done on a small subset of the artists images, as such the output of this LoRA is not an accurate representation neither in quality or style of the source material. Go support the artist if you want the good stuff.

    Description

    Initial release

    FAQ

    LoCon
    Other

    Details

    Downloads
    680
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/4/2026
    Deleted
    5/10/2025

    Files

    Tsuda Nanafushi Training Tags.zip

    Mirrors

    tsuda_nanafushi-NAI-LyCORIS.safetensors