CivArchive
    Claudia Photodromm (SD 1.5, Pony, Flux, Wan Video, Hynyan Video) - v1.5
    NSFW

    Claudia Photodromm

    aka Busty Claudia / Claudia / Claudia E / Claudia F / Nina

    Model works good in 0.7-1.1 strength range.

    For SD1.5 Loras I recommend Westmix v1, nextG, endlessReality, epicrealism and photon models. It works with anime and other models too, with interesting results.

    For Pony Lora I recommend using Pony Realism and vividPDXL_Real models.

    For Flux regular Flux 1.D

    Please share feedback so I can improve it

    Description

    Changes since v1

    1. Trained on all the published Claudia Photodromm image sets. This resulted in 285 images, which I had a hard time training a Lora on, poses were weird and it looked overtrained.I split the dataset into two halves, trained them separately. After I merged the two resulting Loras, and updated the metadata to reflect the image count and tags. If you have a better suggestion for large datasets please share

    2. Cleaned up the dataset tagging, and made it more consistent, added poses, hand positions, etc. LMK if you see weird things.

    3. Re-uploaded model with fixed metadata, where Lora name in prompt shows up the same as filename. Tensors are the same, model behaves exactly that same, as one v1.5 I uploaded few days ago

    FAQ