CivArchive
    Preview 42378956Preview 42379099Preview 42379295Preview 42379303Preview 42379298Preview 42379294Preview 42379296Preview 42379305Preview 42379297Preview 42379299Preview 42379287Preview 42379284Preview 42379304Preview 42379300Preview 42379290Preview 42379291Preview 42379301Preview 42379286Preview 42379302Preview 42379292

    Hassaku aims to be a anime model with a bright and distinct anime style.

    You can run Hassaku XL and use its API on SinkIn: https://sinkin.ai/m/JWknjgr

    My Discord for everything related to anime models and art.

    ____________________________________________________________
    Supporters:

    Thanks to my supporters Riyu, SETI and Kodokuna

    ____________________________________________________________
    Using the model:

    • The model is trained using images with minimal disruptive elements such as floating text, logos, speech bubbles, and signatures. If any of these elements are present in an image, please include the prompt "signature" as a negative prompt

    • Metadata and franchise tags are excluded—please do not use them. Tags such as "highres" and franchise-related tags like "re:zero kara hajimeru isekai seikatsu" are not used in training

    • Look at the example images, to see how the model should be used

    • Model is trained to be not complicated in use, tag order:
      First are the number of person, then character names, rest.
      Example: 1girl, rem \(re:zero\), standing, masterpiece, upper body

    • NoobAIs Loras working for the most part better in compare to Illustrious loras

    • Here are some resolution options for SDXL:

      • 1536 x 640

      • 1344 x 768

      • 1216 x 832

      • 1152 x 896

      • 1024 x 1024

      • 896 x 1152

      • 832 x 1216 (most recommended)

      • 768 x 1344

      • 640 x 1536


    ______________________________________________________

    Version and License info:

    Description

    This model was trained on more up-to-date data, it can be considered between Illustrius and NoobAI-XL in terms of its look.

    It don't have a strong style merge, like Wai or NTR, to have stronger responding artist tags.

    The base model is Illustrious-XL, trained on a dataset ranging from 70k to 440k images (to update Illustrious-XL), primarily making sure that newer Genshin characters, ZZZ and Wuthering Waves characters are trained in.

    It was later merged with WAI-NSFW-illustrious-SDXL, to achieve a more consistent style, but it loses a bit of my character training, like details on clothes (and loses appearence of characters with lower image counts).

    If you want 1to1 clothes like of newer characters from ZZZ, the clothes are mostly off and wrong in detail, i will fix that in the next version.

    Checkpoint
    Illustrious

    Details

    Downloads
    2,113
    CivitAI Status
    Available
    Created
    11/27/2024
    Updated
    8/23/2025
    Deleted
    -