CivArchive
    [SDXL] Artist Style: shiguren39 - v6.311P[Illustrious v1.0]
    NSFW
    Preview 71712716
    Preview 71712779
    Preview 71712783
    Preview 71712800
    Preview 71712806
    Preview 71712862
    Preview 71712958
    Preview 71712963
    Preview 71712969
    Preview 71712998
    Preview 71713007
    Preview 71713027
    Preview 71713032
    Preview 71713033
    Preview 71713053
    Preview 71713056
    Preview 71713063
    Preview 71713095
    Preview 71713118

    SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.

    Version naming convention: MajorVersion.MinorVersion [BaseModel]

    MajorVesion: For big updates that can apply to any style LoRA. For example, training parameter update.

    MinorVersion: For small updates that only apply to this LoRA. For example, epoch selection, removing a certain image from dataset.

    BaseModel: SDXL LoRA/LyCORIS works best on the model that it was trained on.


    TonightXiao_JinXiao's original account was recently banned. Here is his new account: https://civarchive.com/user/TonightXiao_Shyaku

    Description

    FAQ

    Comments (3)

    doctor111Apr 23, 2025· 1 reaction
    CivitAI

    楼主认为illustrious1.0比起wai和noob哪个训练表现更好呢,我自己也在做一些画风lora训练,使用的多是wai13.0,但总感觉生成的图片画风在细节上被大模型覆盖而非lora所训练的图片画风

    silvermoong
    Author
    Apr 23, 2025

    在我看来区别不大,画风lora会把模型本身的风格给覆盖了,不同的模型就是不同的知识量和肢体稳定度的区别

    ACSAIApr 24, 2025· 3 reactions
    CivitAI

    thanks for making the lora

    LoCon
    Illustrious

    Details

    Downloads
    810
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/22/2025
    Updated
    8/25/2026
    Deleted
    -

    Files

    shiguren39XL_il1_lokr_V6311P.safetensors

    Mirrors