CivArchive
    Preview 5319191
    Preview 5319193
    Preview 5319192
    Preview 5319195
    Preview 5319194
    Preview 5319196
    Preview 5319197

    model for asians

    Description

    While making t3 (ver11-beta), I felt like I used too much real-life, so I made a 2.5D version for the first time. I think 2.5D is more difficult than I thought because it's my first time making it, but it was fun. It is unclear whether the next version will be made. ^^

    FAQ

    Comments (5)

    ohahaps2Jan 14, 2024· 6 reactions
    CivitAI

    文件那么大 不如直接用xl。何况升级还需要调用大模型,考虑下显存小的行吗,重点,做样本图都很好 ,使用lora拟合性差,一群人在一起,男性全部都化妆,美瞳,睫毛过长。如果是个女性大模型,那选择性太多了,感觉就是那几张样板脸的混合

    darksagaq12926
    Author
    Jan 14, 2024· 3 reactions

    第一次做2.5D,不太熟悉,无聊才做的^^ t3 ver11 beta 正在完成。 虽然是测试版,但我已经很满意并测试了^0^

    Anarchism_007Jan 20, 2024· 1 reaction

    别喷,多给点善意的鼓励!!!

    darksagaq12926
    Author
    Jan 20, 2024

    适当的批评是可以的,因为它可以填补空白。 ^0^ 接下来是真人秀~

    zyd232Jan 26, 2024

    大有大的好处嘛——你若要小的,可以下个 Model Toolbox 插件,自己修剪模型,一般修到2GB的大小效果也不会差。女性特征污染男性人物的问题并不是这个模型独有的问题,而且主要是 prompt 污染的问题,有这方面需求的话试试 Composable Lora 插件吧。

    Checkpoint
    SD 1.5

    Details

    Downloads
    1,505
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/9/2024
    Updated
    5/14/2026
    Deleted
    -

    Files

    t3_25DVer1.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)
    ShakkerAI (1 mirrors)

    Available On (1 platform)

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