CivArchive
    body slider shape - v1.0
    NSFW
    Preview 76886124
    Preview 76886169
    Preview 76886609
    Preview 76886971
    Preview 76886977
    Preview 76887030
    Preview 76887209
    Preview 76887463
    Preview 76887667
    Preview 76888276
    Preview 76888702
    Preview 76888733
    Preview 76888825

    Model generates images of beautiful girls and women with thin waist, natural breasts and larger breasts

    Adjusted model with 4 loras:

    abel完美身材,perfect body

    Top

    BreastShaper_splendid_droplets (Flux) v3.0

    Big round breasts FLUX

    You need these files inside each corresponding folder for the model to work correctly. It works with stable diffusion forge and comfyUI:

    ae.safetensors, clip_l.safetensors and t5xxl_fp8_e4m3fn.safetensors

    It is strictly prohibited to distribute, inside and outside civit ai, this template or post it anywhere or on hosting services, on third party image generation services, you can use it for personal use, if you know who distributed it without my consent , report it immediately.

    Resolution settings:

    Standard resolutions 512 x 768, 768 x 512, 540 x 960, 640 x 960, 960x640 and 1024 x1024

    Resolution: 540x540 select the Hires.fix checkbox, result 1080 x 1080 pixels

    Note: I am testing the sampling methods and I will add the others to the settings.

    Use these recommended settings for generation:

    Sampling method: euler

    Sampling steps: 20

    Distilled CFG Scale 3,5

    CFG Scale: 1

    Skip clip: 1

    Description

    Model generates realistic and photographic images, experimental version, may have images with serrations, and bad hands, is functional

    FAQ

    Comments (2)

    md29Oct 28, 2025
    CivitAI

    I am interested in using the model. I downloaded it and placed it in the stable diffusion folder. I have clipL.safetensors in the textecoders folder and t5xxl_fp8_e4m3fn also located there. I tried to load the model with checkpoint loader and it gives me an error, also with unet loader and dual clip and it also gives me an error... size mismatch for img_in.weight: copying a param with shape torch.Size([98304, 1]).... What solution can you give me? Thank you!

    Dxdesignia
    Author
    Oct 28, 2025

    Use this tutorial and it will work correctly with stable diffusion forge or sd-webui-forge-neo: https://civitai.com/articles/19010/learn-how-to-use-nf4-flux-models-with-stable-diffusion-forge