CivArchive
    Bra v6 fix - v1
    NSFW
    Preview 2144766
    Preview 2144915
    Preview 2144829
    Preview 2144871
    Preview 2144817
    Preview 2144788
    Preview 2146398
    Preview 2146399
    Preview 2147116
    Preview 2147118
    Preview 2147313
    Preview 2147325

    This is a Bra V6 Fixer.

    The Bra V6 is a fantastic model, but getting a good handle on the Brav6 prompts could be a bit of a challenge.

    The Bra V6 fixer helps the prompts work a little more as intended, and the LoRAs come out a bit nicer.

    Recipe

    procedure: almost the same method applied for "chillout NFSW fixer"

    1. try to interpolate input_blocks of Bra V6 to chilloutmix to make LoRA friendly

    2. try to interpolate output_blocks of Bra V6 to dreamshape v8

    3. make a checkpoint

    4. make LoRA using Supermerger (by https://github.com/hako-mikan)/ make Lycoris/Locon version using LyCORIS extract command line tool foundat LyCORIS github project (by https://twitter.com/KBlueleaf)

    Please see the following article.

    How to make your checkpoint LoRA friendly?

    Usage

    • Lora version v1:

      • "<lora:Brav6fix_v1:1>" : LoRA weight ratio could be 0.5~1.5

    • Lycoris/Locon version v1:

      • "<lyco:Brav6fix_locon_v1:0.9>" : Lyco weight ratio could be 0.5~1.5

      • for Lycoris version : download "locon v1" version and copy into stable-diffusion-webui\models\LyCORISsubdir. (it is better to rename downloaded file correctly if the filename is not "Brav6fix_locon_v1.safetensors")

      • from webui 1.5.x(?) you can use <lora:Brav6fix_locon_v1:0.9> without extension. (in this case, you have to copy lyco/locon file into models/LoRA

        • but it seems a bug exists that makes Lycoris not work properly.

    License

    The same License of Bra V6

    Description

    • 2023/08/22 - first release out

    FAQ

    Comments (4)

    StraitjacketAug 22, 2023· 1 reaction
    CivitAI

    This looks very interesting, as I've noticed BRA6 definitely has some major issues with many loras especially when compared to other models- pardon my ignorance but how does this work?

    Do you just use this at 1 strength and then activate your other loras for better results?

    mixboy
    Author
    Aug 22, 2023· 2 reactions

    the principle is simple. make the checkpoint model similar to the Chilloutmix using a fitting program.

    recipe/procedure described in the article https://civitai.com/articles/1784/how-to-make-your-checkpoint-lora-friendly

    thezlowman731Aug 22, 2023· 1 reaction
    CivitAI

    in the Details > Type, it says LORA;

    in the Details > Trigger Words, it says <LYCO:BRAV6FIX_V1:1.0>;

    in one of the examples promopts, it says <lora:Brav6fix_v1:1>.

    which one is it....?

    mixboy
    Author
    Aug 23, 2023

    thanks for your bug reporting. fixed now (<lora:Brav6fix_v1:1> is right syntax. case sensitive)

    and...

    Brav6fix_v1 is LoRA, Brav6fix_locon_v1 is Lyoris(Locon). LoRA needs "<lora:..." syntax, Locon needs "<lyco:" syntax, but, the recent webui support both using "<lora:" syntax.

    (and press copy&paste icon then you can get the right text as "<lora:Brav6fix_v1:1>" (case sensitive)

    LORA
    SD 1.5

    Details

    Downloads
    4,006
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/21/2023
    Updated
    5/14/2026
    Deleted
    -
    Trigger Words:
    <lora:Brav6fix_v1:1>

    Files

    Brav6fix_v1.safetensors

    Mirrors

    TensorFiles (1 mirrors)