CivArchive
    Zoot's Tweaked Base SDXL For Finetuning Or Lora Training - v1.0
    Preview 1

    This is the base SDXL checkpoint, with the following changes:

    • DPO Lora merged in at 0.25 model / clip strength

    • SPO Lora merged in at 0.75 model / clip strength

    • Baked VAE replaced with SharpSpectrumVAE XL

    This is basically an opinionated set of changes I found after a bunch of testing to provide an overall better basis to work off of.

    Description

    <p>Initial Version.</p>
    CHECKPOINT
    SDXL 1.0

    Details

    Downloads
    546
    Platform
    TensorArt
    Platform Status
    Available
    Created
    9/2/2024
    Updated
    9/8/2024
    Deleted
    -

    Files

    zootsTweakedBaseSDXLFor_v10.safetensors