CivArchive
    Preview 87081144
    Preview 87144029
    Preview 87144041
    Preview 87144052
    Preview 87144055
    Preview 87144128
    Preview 87150276

    v3

    Changed the base model to “Seele-NoobAI-SDXL v2.1”.

    https://civarchive.com/models/1445275?modelVersionId=2281915

    Generation at 2048x2048 resolution is now possible.

    Recommended prompt

     My Settings(anime): masterpiece, best quality, newest, very aesthetic, absurdres, highres, high resolution, (megami:1.4) (magazine:0), (flat color:0.7), (anime screenshot:1.4)

     Seele-NoobAI-SDXL: masterpiece, best quality, newest, absurdres, highres, high resolution

     My Settings(old): very aesthetic, masterpiece, best quality, newest, vector trace, absurdres, highres, anime coloring

    Negative Prompt

     My Settings(anime): text, word, text watermark, (overexposure:1.4), (megami:0) magazine, realistic, worst quality, low quality

     Seele-NoobAI-SDXL: worst quality, normal quality, old, early, low quality, lowres, text, word, text watermark, Color cast, Blurred background, Halo, Colorful spots

     My Settings(old): worst quality, normal quality, low quality

    CFG: 3-6


    noob-vpred1

    This is an anime model merged based on noobAI XL.

    V-Pred v1.0 was used.

    Recommended prompt: very aesthetic, masterpiece, best quality, newest, vector trace, absurdres, highres, anime screenshot

    Negative Prompt: worst quality

    CFG: 5

    Sampling method: Euler_Smea

    advance_eular_sampler_extension: https://github.com/licyk/advanced_euler_sampler_extension.git

    Please comply with NoobAI XL for licensing.

    I am using A1111 WebUI and WebUI Forge. Please note that I am not familiar with ComfyUI.

    Description

    This model was provisionally merged in response to an inquiry from another user asking whether an illustrious version was planned.

    At present, it’s only capable of producing reasonably clean linework. With sufficient prompt enhancement and the use of tools like prompt completion, it may be possible to generate somewhat acceptable outputs.

    Test settings:
    CFG: 7
    Resolution: 2048x2048

    I’m personally not very fond of this model, but I’m publishing it in the hope that it might serve as a base for someone else's merging experiments.
    I just wish illustrious V3.5 v-pred would be released soon.

    FAQ

    Checkpoint
    Illustrious

    Details

    Downloads
    443
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    7/8/2025
    Updated
    8/9/2025
    Deleted
    8/7/2025