CivArchive
    KoreanDollLikeness (v2.0) - v2.0
    NSFW
    Preview 355883
    Preview 355890
    Preview 355889
    Preview 355888
    Preview 355887
    Preview 355886
    Preview 355885
    Preview 355884

    Hi, this is author Kbr, I am back and I bring you new version of KoreanDollLikeness.

    (Please double check the naming of the LORA file when using sample images generation data, Civitai love to rename the LORA file automatically into something different)

    If you are wondering where are the older versions of my other LORAs( KDL, JPL, TDL), you can find them here on huggingface: https://huggingface.co/Kanbara/doll-likeness-series

    My Twitter: https://twitter.com/KbrLoras
    My Pixiv: https://www.pixiv.net/en/users/92373922

    I usually post my works on Twitter and Pixiv.


    You can now use this model at:
    - SinkIn
    - DazzleAI (Link to discord: https://discord.gg/pq2RmzfaTx)
    - Tensor.art (free online generation)

    Please consider supporting me at: https://ko-fi.com/kbrloras

    It takes time and effort to collect training materials, training, testing LORAS, I would appreciate your support!

    ----------------------------------------------------------------------------------

    Introduction
    1. This version or KDL does not necessarily mean it is better or worse than v10 or v15, it is a different version that feature another set variety of faces.

    Recommended settings:

    • Make sure you are aware on the usage instructions of LORA

    • VAE: vae-ft-mse-840000-ema-pruned (For realistic models)

    • Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers)

    • Steps: 20 to 35

    • Clipskip: 1 or 2

    • Upscaler : Latent (bicubic antialiased)

    • CFG Scale : 5 to 9

    • LORA weight for txt2img: anywhere between 0.2 to 0.7 are recommended

    • Denoise strength for img2img: 0.4 to 0.7

    • It is also recommended to mix this LORA with my other DollLikeness LORAs for interesting effects


    ----------------------------------------------------------------------------------

    License

    This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:

    1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content

    2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license

    3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) (Full license here: https://huggingface.co/spaces/CompVis/stable-diffusion-license)

    Additional Add-ons to license/notes

    1. You shall take full responsibility for any creative work that uses this model

    2. Refrain from using this model for malicious intent, harm, defamation, scam or political usages. It may impair and discourage the author from producing more works.

    Disclaimer

    Creation of SFW and NSFW images is user's decision, user has complete control over to generate NSFW content whether or not.

    ----------------------------------------------------------------------------------

    FAQ

    • Q: Why can't I produce the same pictures as you?

    • A: Sorry I don't share my prompt, you may check the recommended settings, but you may ask me for advice on Twitter or Pixiv

    • Q: Where did your first Civitai account went? why did it disappear?

    • A: I decided to delete the account due to news of controversial scam reported by online media outlet, I hope it will not happen again.

    • Q: What is the difference of each version upgrade?

    • A: Version upgrade does not mean it will fix hands or legs, it is mainly difference of the face of the LORA, newer versions have wider range of faces.

    • Q: Will you release all your other LORAs?

    • A: Yes, maybe, but I would like to keep certain LORA to be exclusive to fans or supporters in the future through fanbox/ko-fi

    • Q: Do you take requests or commissions on making custom LORAs?

    • A: I might do community voting for requests, if you are somehow interested in a custom/exclusive LORA, you may contact my through Pixiv or Twitter for discussion

    Description

    FAQ

    Comments (32)

    otakuisgodMar 29, 2023· 2 reactions
    CivitAI

    welcom back

    242424Mar 29, 2023· 8 reactions
    CivitAI

    Oh, my God, you're finally back！！

    yaogeMar 29, 2023· 2 reactions
    CivitAI

    unbelievable！

    zjx1170583313660Mar 29, 2023· 9 reactions
    CivitAI

    王者归来！！！

    NotAPersonJustACatMar 29, 2023· 3 reactions
    CivitAI

    Are there improvements compare to the previous upload?

    geopolya175Mar 29, 2023· 2 reactions
    CivitAI

    Unbelievable good !!!

    ccxczxcMar 30, 2023· 5 reactions
    CivitAI

    On my computer, I get this error: Upcast cross attention layer to float32 is turned on, but there is a problem, what is the solution?

    -

    modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

    -

    Kbrloras
    Author
    Mar 30, 2023

    Make sure to use the correct vae

    KevinKang_NMar 30, 2023· 2 reactions
    CivitAI

    welcome back, 老哥

    MydearMar 30, 2023· 2 reactions
    CivitAI

    你确定你是原作者吗，都是三月才开的号

    Kbrloras
    Author
    Mar 30, 2023· 3 reactions

    我消失一个月当中有很多冒充用户吗

    BloodsugaMar 31, 2023· 2 reactions

    他是原作者，我担保 :)

    diaoxieApr 4, 2023

    他是 tasuku也說他是

    spooliMar 30, 2023· 7 reactions
    CivitAI

    他来了他来了 他带着李小璐来了

    KazeSwiftMar 30, 2023· 2 reactions
    CivitAI

    welcome back!

    soullessMar 30, 2023· 2 reactions
    CivitAI

    good to have you here

    242424Mar 30, 2023· 19 reactions
    CivitAI

    japandoll and taiwandoll plz!!!!!!!!

    AverageSNJMar 30, 2023· 2 reactions
    CivitAI

    Welp. Hope your not one of those ch*nks who pretends to be the original author...

    Kbrloras
    Author
    Mar 30, 2023

    No worries because I am the original author, which I can guarantee

    WerranMar 31, 2023· 6 reactions
    CivitAI

    modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

    beasttheorcApr 4, 2023· 1 reaction

    That was a bug with CivitAI a few days ago, most Lora and Models downloaded here came with this bug. Just download again or search somewhere else. Commenting in case you're still stuck with this

    CryzeraApr 7, 2023

    @beasttheorc  it's not a bug. it happens when in a img2img when you don't give enough info about the picture you uploaded

    YuikunApr 4, 2023· 2 reactions
    CivitAI

    not sure if you really are the original author, but anyway, welcome back

    gghihApr 5, 2023· 9 reactions
    CivitAI

    well comeback GOAT

    maiowxcxApr 7, 2023· 10 reactions
    CivitAI

    support my man on https://ko-fi.com/kbrloras

    guys dude need new GPU

    axicecMay 27, 2023

    don't we all.

    qishimeshiAug 26, 2023· 20 reactions
    CivitAI

    第一张图真的好像周姐……

    2087746Aug 31, 2023· 3 reactions
    CivitAI

    Hi does this combine well with photorealistic asian women loras or will it change the faces?

    Dr_DreamSep 29, 2023· 13 reactions
    CivitAI

    SDXL model?

    jameshard0409531Dec 1, 2023· 8 reactions
    CivitAI

    very nice model! I tried it also using 1gen and its nice too. =D

    CrankerrrDec 31, 2023· 9 reactions
    CivitAI

    Found it randomly but maybe the best base model overall!

    ehdgo1101651Feb 9, 2024· 8 reactions
    CivitAI

    Is there a version 1.0?

    LORA
    SD 1.5
    by Kbrloras
    Download (Beta) View on CivitAI
    photorealistic
    women
    style
    korean
    asian

    Details

    Downloads
    205,963
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/29/2023
    Updated
    5/16/2026
    Deleted
    -

    Files

    koreanDollLikeness.safetensors

    Size:
    144.11 MB
    SHA256:
    00483a2a78cec31880128ec2da827349ebaaccd7d2d1d35836baebecf006d983

    Mirrors

    HuggingFace (134 mirrors)
    CivitAI (3 mirrors)
    TensorFiles (1 mirrors)
    CivitasBay (1 mirrors)
    TensorArt (1 mirrors)

    Available On (1 platform)

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

    CivitasBay
    KoreanDollLikeness (v2.0) - v2.0