CivArchive
    Grav_Qunqun_TW - V2
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    This is a V3 Qunqun, we have input some new image to makes it more better.

    煩請愛峮朋友不要再在我的圖按投訴,這對大家沒好處,大家都喜歡峮,想多做點美美圖出來,不要老投訴害大家都看不到好的參數。

    PLS! No NSFW content share of this model.

    我的製作只作個人用途,請勿未經我的許可轉載到其他討論區或作盈利用途!

    If you like our model, please buy me a coffee and supporting for future project.
    https://ko-fi.com/apsrcevo

    Please give us a 5 star rating.
    Commercial customization LoRA project are welcome.

    After download this model, try to share with us about your finding.
    Again, not for commercial use and she is not a existing person.

    Please use ChilloutMix and based on SD1.5

    • 768,768 image

    • Use DPM++ 2M Karras or DPM++ SDE Karras

    • Face restore: 0.9

    • Denoising strength: 0.7

    • Hires. fix: on

    • Hires step: 18

    • Sampling step: 16

    • Denoising: 0.7

    Description

    FAQ

    Comments (2)

    SD_APS_LAU
    Author
    Mar 27, 2023· 2 reactions
    CivitAI

    我做了一個很峮的圖給大家參考,用V1的,不是V2。我兩個有時都會用的。其實兩個都能生成很峮的圖,只是參數問題,V2亦都解像高一點。

    用V1生成的新圖,留意Restore Faces我在Setting調整為0.6,不是0.5。這個在Info的Prompt不會看到,但作為提議去設定。其餘按Prompt的都可以。

    AcreatorI2023Jul 18, 2023
    CivitAI

    可不可以用個指向性高點的觸發詞.

    LORA
    SD 1.5

    Details

    Downloads
    4,992
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    3/26/2023
    Updated
    5/7/2026
    Deleted
    5/23/2025
    Trigger Words:
    taiwan
    cheerleader

    Files

    QunqunV2.safetensors

    Mirrors

    CivitAI (1 mirrors)
    TensorFiles (1 mirrors)