CivArchive
    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

    Goddess Project

    --Formerly Uncensored Females--

    Standalone Checkpoint - Goddess works in FORGE only

    DO NOT LOAD a separate VAE, TE, or CLIP unless using GGUF

    This version is a mixed precision Flux Dev model, with limited UNET changes to allow for feminine anatomy.

    • Run this model in automatic FP16 Lora mode NOT NF4

    • This model is full precision in BF16 UNET with mixed precision (NF4) on the TE blocks

    • This model fits in a 24GB card and could be run in GPU only mode as such

    • High speed BF16 with a slightly lower prompt accuracy compared to the 33GB full model

    Per the Apache 2.0 license FLAN is attributed to Google


    This model is a training using many individuals with known ages and 2257 forms, it has also been merged to try and ensure that no known individuals can be reproduced. However FLUX seems to like to learn faces even with less then 10% data rather then merge them into a new face.

    Description

    Version 3 in NF4 format

    FAQ

    Comments (7)

    mscorpion7285Sep 30, 2024· 2 reactions
    CivitAI

    Thx bro.Happy to play with the nf4 checkpoint now.

    feanorkndOct 1, 2024
    CivitAI

    all boobs like the same?! just a question after having a look at images..

    Felldude
    Author
    Oct 1, 2024

    Anything not described tends to default, hair color, breasts size etc

    Felldude
    Author
    Oct 1, 2024

    And just like text adherence it seems to be hit and miss

    sevenof9247Oct 1, 2024

    take my lora :)

    Felldude
    Author
    Oct 1, 2024

    A odd behavior I have noticed is doing an unguided image to image up scaling seem to produce the best results, even removing 4k, skin detail etc

    Felldude
    Author
    Oct 1, 2024

    @sevenof9247 I am assuming your LORA is UNET only training also, that could be playing a large part in this as well

    Checkpoint
    Flux.1 D

    Details

    Downloads
    2,204
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/30/2024
    Updated
    5/11/2026
    Deleted
    -

    Files

    uncensoredFemalesFLUX_ggufDevV5Q8.gguf

    Mirrors

    godessProjectFLUX_ggufDevV7Q8.gguf

    Mirrors

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.