CivArchive
    Morena Baccarin SDXL + FLUX - v1.0 FLUX
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Flux:

    Trained on FLUX1.dev with 237 images

    Tested with ComfyUI and Forge...

    SDXL:

    Trained on SDXL 1.0 vae fix with 281 images.

    The result of another test training trying to reduce the file size without compromising (too much) on likeness/quality and without resizing the model afterwards...

    And again, there is still a lot of room for improvement..

    No VAE, hiRes fix or refiners were used for the example images...

    Description

    Trained on FLUX1.dev with 237 images..

    Tested with ComfyUI and Forge..

    FAQ

    Comments (3)

    MalessarAug 28, 2024
    CivitAI

    Pls train this for pony too

    mrneonAug 28, 2024
    CivitAI

    This lora produces very mangled images for me, and no likeness at lower weight.

    doveshipAug 28, 2024· 2 reactions
    CivitAI

    This looks good. I will say though that, given your Firefly focus, it feels like you missed a shot by not generating a picture that captures her as Inara for your showcase (the Flux one)

    LORA
    Flux.1 D

    Details

    Downloads
    1,115
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    8/28/2024
    Updated
    5/4/2026
    Deleted
    5/25/2025
    Trigger Words:
    morena_baccarin

    Files

    MorenaBaccarinF1D.safetensors

    Mirrors

    TensorFiles (1 mirrors)