CivArchive
    FormCorrector Anatomic - v1.0
    Preview 23985440
    Preview 23985442
    Preview 23985438
    Preview 23985441
    Preview 23985448
    Preview 23985449
    Preview 23985439

    This is a Flux Dev retrain of my SDXL model Frosting Lane Redux. I used Ostris' AI Toolkit trainer.

    Special thanks to @ostris for creating an excellent codebase for model training. https://github.com/ostris/ai-toolkit/tree/main

    This is the first test of training a model, and all licensing conditions for the Flux Dev model apply. https://huggingface.co/black-forest-labs/FLUX.1-dev. It's a great model!

    A huge thank you to Datacrunch.io for generously providing their resources for training and support. I highly recommend them.

    The purpose of this model is to enhance understanding of anatomy and improve prompt comprehension. The differences are subtle but may help you correct some mistakes. I tested it on approximately 300 generations, and in 90% of the cases, the results were better in terms of anatomy and realism. It might distort your text, so don't be afraid to experiment and adjust the model's weight. I tested it using seed 0 with a model weight of 1. The model was trained on approximately 5,000 images. If the test results are mostly positive, I will train it on a larger dataset. I welcome any feedback in the comments—feel free to share any errors or shortcomings of the model — this is just an experiment.

    (the first image features the use of a LoRA, while the second image does not.)

    Description

    FAQ

    Comments (11)

    raidmachine132017712Aug 13, 2024
    CivitAI

    It's not working, and size is too big with flux itself being huge model adding another 1.2GB will be machine killing.

    Sa_May
    Author
    Aug 13, 2024· 2 reactions

    I'll think about how to reduce the size

    jr81Aug 23, 2024

    It did not work for me, in Comfy UI, with Flux FP8.

    But it worked with Flux in GGUF formats, which require less resources. 

    https://github.com/city96/ComfyUI-GGUF

    wiizAug 14, 2024· 1 reaction
    CivitAI

    Good model, but the network rank is too high meaning the file size will be too large for most consumer cards.

    jr81Aug 23, 2024

    It did not work for me, in Comfy UI, with Flux FP8.

    But it worked with Flux in GGUF formats, which require less resources. 

    https://github.com/city96/ComfyUI-GGUF

    JobeeAug 16, 2024
    CivitAI

    Too big for me to handle

    jr81Aug 23, 2024

    It did not work for me, in Comfy UI, with Flux FP8.

    But it worked with Flux in GGUF formats, which require less resources. 

    https://github.com/city96/ComfyUI-GGUF

    JobeeAug 24, 2024

    @jr81 thanks

    Askeladd_Aug 25, 2024

    That's what my GF never tells me

    harshhpatel0204765Apr 14, 2026
    CivitAI

    Can you provide me with the image categories, their resolutions, and descriptions, as well as the training parameters, because I am facing the same body anatomical issue?

    harshhpatel0204765Apr 22, 2026
    CivitAI

    @Sa_May Can you provide me with training inference params because I am facing the same issue, and I have tried lots of models for fine-tuning, but still no improvement on the body anatomical issue.

    LORA
    Flux.1 D

    Details

    Downloads
    510
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/12/2024
    Updated
    5/19/2026
    Deleted
    -

    Files

    Test_real_photo_Flux.safetensors

    Mirrors

    Available On (1 platform)

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