CivArchive
    Haguhagu Style - v1.0 SD 1.5
    NSFW
    Preview 8240971
    Preview 8240976
    Preview 8240970
    Preview 8240978
    Preview 8240974
    Preview 8240973
    Preview 8240975
    Preview 8240969
    Preview 8240968
    Preview 8240977

    If you like my content consider supporting me! ๐Ÿ˜Š

    1 Cookie = Early access to future releases! ๐Ÿชโค๏ธ

    Locon trained on the style of Takamichi for Pony Diffusion v6 XL based models.

    All sample images uses a weight of 0.8 and uses no trigger words.

    I actually added a trigger word for this one: h4guh4gu, but it is not necessary to use it. For instance, all the sample images don't use it.

    This is another one that turned ou pretty good in my opinion! Same training parameters.

    If you have any tips or more advanced knowledge for better training with Pony let me know through Chat/DM.

    Disclamer

    All the models that I have developed and published on this platform are for entertainment purposes only. They are derived from the base Stable Diffusion model, which means it also includes its inherent issues, limitations and unfiltered capabilities. With that in mind, I am in no way responsible for any content that the user creates with malicious intent while using any of these models. The user assumes complete responsibility for the misuse of these tools and any unethical content created with them. This disclaimer is subject to the laws of the United States of America and the state of California. I reserve the right to remove or report any content that violates the terms of service, ethical standards, or applicable laws.

    License conditions

    Haguhagu Style for Pony Diffusion v6 XL and Stable Diffusion 1.5 ยฉ 2024 by Pettan Koutei is licensed under Attribution-NonCommercial-ShareAlike 4.0 International

    Description

    ๐Ÿ” Version info:

    Same as v1.0 but trained on SD1.5 NAI instead of Pony.

    ๐Ÿ“‹ Training Parameters:

    • Base Model: NAI

    • Training Resolution: 576

    • Training Batch Size: 2

    • Type: LoCon

    • DIM / Alpha: 32 / 16

    • Conv Dim / Alpha: 24 / 6

    • Train On: Unet + TE

    • Optimizer: Prodigy

    • Min SNR Gamma: 8

    • Bucket Resolution: 512 - 1024

    • Bucket Steps: 64

    • Noise Offset: Normal (0.035)

    • Image Count: 70

    • Epochs: 24

    • Repeats: 2

    FAQ

    Comments (3)

    shlim24852365Mar 20, 2024ยท 3 reactions
    CivitAI

    I like your models! Thank you.

    pettankoutei
    Author
    Mar 20, 2024

    Thanks! ๐Ÿฅฐ

    PlayanGaemsMar 29, 2026
    CivitAI

    Any chance for an Illustrious version?

    LoCon
    SD 1.5

    Details

    Downloads
    528
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/20/2024
    Updated
    5/13/2026
    Deleted
    -

    Files

    haguhagu-lyco-nai-v1.safetensors

    Mirrors