CivArchive
    psxCBstyle - Photography Style LoRA - v1.0
    NSFW
    Preview 109947363
    Preview 109947408
    Preview 109947357
    Preview 109947394

    What Is It?

    This LoRA is trained to provide a dark, dramatic, sleazy style to your realistic image generations. It has been tested with standard 1girl prompts but not tested with NSFW, or groups. It may have effect on faces, image style will lean towards model type poses.

    How To

    All generations in the samples use only this LoRA applied by itself and a face detail node. Generated using euler/beta @ 32 steps OR res_2s/bong_tangent @ 20 steps. You may notice at strengths near 1.0 and higher the model can cause some issues with hands, and backgrounds. I've left these in the examples.

    Suggested Weight: 0.4 - 1.0

    Training Notes

    Trained with 12 captioned images at 768, 1024. No effort was made to train NSFW concepts.

    While I have been able to use this with no keyword applied at all, psxcbstyle will enforce the image style, I also suggest pushing for slight or full fisheye lens effects.

    Sample (left 1.0 str, right 0.0)

    Description

    FAQ

    LORA
    Flux.1 D

    Details

    Downloads
    140
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/12/2025
    Updated
    4/27/2026
    Deleted
    -
    Trigger Words:
    psxcbstyle

    Files

    psxCB_Style_v2_FLUX.1.safetensors

    Mirrors