CivArchive
    Preview 94447472
    Preview 94447450

    ->NoobAI V-Pred | PonyDiffusion | SD 1.5


    Please, check the description, there is a little bit of useful information.


    Inеtroduction:

    This LoRA is supposed to represent Jadf's artstyle.

    Please, be sure to use the same positive and negative quality prompt for better result.


    Compatibility:

    • Humans: great

    • Anthros: great

    • Ponies: great

    • Multiple characters: great

    • Character LoRAs; great

    • Unique characters: great


    Recommendations:

    • Trigger word - jadf (v4+)

    • Trigger word - jdf (v3)

    • 1.0 emphasis

    • Clip Skip 1

    • CFG 5

    • NoobAI 1.0 V-Pred for generations (Main)

    • NoobAI 1.0 Eps for generations (Alternative)

    • masterpiece, best quality, highres, absurdres in positives

    • worst aesthetic, worst quality, low quality, bad quality, lowres, flat color in negatives

    • + colorful, saturated, red theme, blue theme for CIvitAI generations

    • CFG Rescale 0.3 - 0.4 (if you're using v-pred version)

    Use anything else in negatives only if you want to avoid or remove something from the image. For example, you don't want to see doors - "door" in negative. Style will look much better without garbage in negative prompt. Just try it.


    Characters (v4+):

    • Jadf-tan

      • black hair, very long hair, blunt bangs, hime cut, red hairband, yellow eyes

    There is still not so much images of her, but character is now working, at least. I hope you'll like this change, and of course, i hope there will be more art of her in the future.


    Credits:

    Trained on NoobAI 1.0 V-Pred. Dataset of 200 pictures (v1), 30 epochs, Clip Skip - 1
    Trained on NoobAI 1.0 V-Pred. Dataset of 300 pictures (v2), 40 epochs, Clip Skip - 1
    Trained on NoobAI 1.0 V-Pred. Dataset of 260 pictures (v3), 40 epochs, Clip Skip - 1
    Trained on NoobAI 1.0 V-Pred. Dataset of 550 pictures (v4). 30 epochs. Clip Skip - 1
    Trained on NoobAI 1.0 V-Pred. Dataset of 600 pictures (v5). 30 epochs. Clip Skip - 1
    Trained on NoobAI 1.0 V-Pred. Dataset of 600 pictures (v5). 30 epochs. Clip Skip - 1

    Really big thanks to:

    • Jadf for beautiful artwork

    • Some good folks from Discord server

    • You, for reading, downloading, liking and reviewing this LoRA

    Description

    What's new?

    1. Added "old artstyle" tag as a regularization tag for negative, now you may use it to avoid flat and simple-styled images from appearing. You'll still get better style even without it.

    2. Expanded dataset up to 600 images

    3. Drastically improved overall style stability

    FAQ

    LORA
    NoobAI

    Details

    Downloads
    323
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/15/2025
    Updated
    4/27/2026
    Deleted
    -
    Trigger Words:
    jadf

    Files

    Jadf v5 - NoobAI 1.0 V-Pred.safetensors

    Mirrors

    Other Platforms (TensorArt, SeaArt, etc.) (1 mirrors)

    Available On (2 platforms)

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