CivArchive
    Kekemotsu | Artist Style | PonyXL | DoRA - v1.0
    Preview 13943048
    Preview 13943046
    Preview 13943043
    Preview 13943044
    Preview 13943049
    Preview 13943050
    Preview 13943054
    Preview 13943055
    Preview 13943052
    Preview 13943062
    Preview 13943059
    Preview 13943057
    Preview 13943061
    Preview 13943058

    Lora trained on kekemotsu's artstyle, should work on all checkpoints based on PonyDiffusion V6, as always please do play with the weights, even over 1.0!

    Remember to only use score_9, score_7_up, in positives, avoid 8 and other scores if you want the style to be at its strongest, applies to past and future loras.

    This is a DoRA LoCON, or a Weight Decompose LoRA LoCON, you need A1111 1.9.0 or newer or apply this PR on your Forge installation, I'll leave the files you need to modify in the files section of this model as "training data", the files go into stable-diffusion-webui\ldm_patched\modules

    Also I made a public spreadsheet so anyone knows what's on the pipeline, link

    Any and all reviews are very much appreciated so I can know what to improve for this LoRA or for other models, thank you~

    I have a Discord server where you can go and bother me about which style I'm working rn, or suggest ones to try my hand at.

    Description

    DoRA
    Pony

    Details

    Downloads
    316
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/6/2025
    Deleted
    4/24/2025

    Files

    kekemotsuArtistStyle_v10_trainingData.zip

    Mirrors

    CivitAI (48 mirrors)

    kekemotsuArtistStyle_v10.safetensors

    Mirrors