CivArchive
    Takamuran Style - v1.0
    NSFW
    Preview 1
    Preview 2
    Preview 3
    Preview 4
    Preview 5
    Preview 6
    Preview 7
    Preview 8
    Preview 9
    Preview 10

    A scribble-like colorful style trained on the characters from the Takamuran circle hgames. LyCORIS version of previously released LoRA.

    How to use
    No trigger word needed. Just prompt 1girl or 1boy and go. The dataset contained a lot of monster girls (spiders, slime, fox etc) so that content should work fine. Also a lot of "muscular female", "dark-skinned female" and all kinds of bigger breasts sizes.
    Approx 75%+ of the dataset is various levels of NSFW but after a bit of wrangling this LyCORIS also handles SFW.

    Recommended sampler: DIMM, DPM++ 2M Karras or any other that doesn't "clean up" the results too much.
    Recommended model: NAI or any other with good/better support for drawing styles like AOM3. For models with realism mixed in I recommend putting "3d" and "realistic" in negatives. Sample images are from AOM3.

    Despite the dataset having little of it some models like to add speech bubbles, putting "speech bubbles" and "text" in negatives helps. You probably want to add "standing", "sitting" or any position since otherwise the many ?????? positions from the dataset tend to blend through.

    Misc
    Trained on NAI at 512 resolution with a dataset of 413 images.
    All images are untouched txt2img, 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 circle if you want the good stuff.

    Description

    Initial release

    LoCon
    Other

    Details

    Downloads
    3
    Platform
    SeaArt
    Platform Status
    Available
    Created
    7/25/2024
    Updated
    8/23/2025
    Deleted
    -

    Files

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.