CivArchive
    Preview 1Preview 2Preview 3Preview 4Preview 5Preview 6Preview 7Preview 8Preview 9Preview 10

    Urushihara satoshi styled LoRA, image trained, SDXL and Pony
    ***may have compatibility issues with a1111/forge, if that's the case let me know and I can release a better version!

    Description

    a1111/forge friendly

    USE THE 2DN-Pony checkpoint for best results!

    this version is a big change:

    • much larger dataset

    • uses a trigger, less of a focus on tags, Trigger: uru5h1h4r4

    • should be more compatible with other LoRA

    • use at a strength from 0.8-1 for best results, if combining with other style LoRA set to 0.4-0.6