CivArchive
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    ***"Running VAE v1.0? You really need Eyes+face Detailer. I also like to run it through Image Adjustments2 and add some Film Grain ***

    ***「VAE v1.0を使うなら、Eyes+face Detailerは必須かも。 あと、仕上げ(post-processing)に Image Adjustments2Photo Film Grainを入れるのがおすすめです。 やり方はいろいろあると思うので、ぜひ情報交換しましょう〜!」***

    ******************************************

    (VAE_V0)VAE edition

    VAE must be added: sdxl_vae.

    About this version

    EastAsian. & V1

    steps: 28-340 cfg: 5-7. 

    Sampler : DPM++ 2M SDE Karras.

     このモデルは、アジア人女性の顔をより正確に再現し、ハーフのような顔立ちの生成を抑え、さらにNSFWな体の動きをより正確に識別できるようになっています。

    This model more accurately represents the facial features of East Asian women, reduces the occurrence of mixed-race appearances, and improves the precision of NSFW body motion recognition.

    Description

    steps: 24-36; cfg: 5-7.

    Sampler : DPM++ 2M SDE Karras.***** VAE: sdxl_vae.****

    Hires upscaler: remacri&4x-UltraSharp,Hires upscale: 2, Hires steps: 10-12

    FAQ

    Checkpoint
    Illustrious

    Looks like we don't have an active mirror for this file right now.

    CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.

    Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.

    Details

    Downloads
    1,415
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    9/21/2025
    Updated
    4/21/2026
    Deleted
    4/21/2026

    Files

    winpicasianrealism_v100.safetensors

    Mirrors