CivArchive
    mikan_(5555) | Artist Style | PonyXL | DoRA - v1.0
    Preview 11352952Preview 11352957Preview 11352966Preview 11352963Preview 11352967Preview 11352959Preview 11352968Preview 11352965Preview 11352964Preview 11352960Preview 11352961Preview 11352958Preview 11352953Preview 11352955Preview 11352954

    Lora trained on mikan_(5555)'s artstyle, you might need card \(medium\) in negatives for some generations or seeds, should work on all checkpoints based on PonyDiffusion V6, as always please do play with the weights, even over 1.0!

    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
    489
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/6/2025
    Deleted
    4/24/2025

    Files

    mikan5555ArtistStyle_v10_trainingData.zip

    Mirrors

    CivitAI (48 mirrors)

    mikan5555ArtistStyle_v10.safetensors

    Mirrors