CivArchive
    xiaozihua - v1.0
    Preview 10005675
    Preview 10005673
    Preview 10005671
    Preview 10005672
    Preview 10005674
    Preview 10005676
    Preview 10005677
    Preview 10005678

    xiaozihua lora

    Training with 50 iterations and 40 epochs, each comprising 3000 steps.

    Since the loss is generally below 0.1 and the fitting degree is high, the weights can be reduced to a range of {0.5-0.8}.

    I usually train using the anything model, which enhances realism significantly.

    Description

    LORA
    SDXL 1.0

    Details

    Downloads
    63
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/16/2024
    Updated
    1/12/2026
    Deleted
    -

    Files

    xiaozihua_SDXL-000002.safetensors

    Mirrors

    Available On (1 platform)