CivArchive
    玩骨 WanGu - v1.0
    Preview 2588738
    Preview 2588737
    Preview 2588741
    Preview 2588759
    Preview 2588768
    Preview 2588775
    Preview 2588783
    Preview 2588790
    Preview 2588791
    Preview 2588793


    My English is not very good, there may be some translation problems, please forgive me.

    I have created another very small model, if anyone likes it I will continue to optimize it.

    我又来上非常小众的模型了,,, 如果有人喜欢我会继续优化。

    首先感谢@遇见清风 提供素材,与我共创。

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

    [Model introduction and parameter recommendations]

    trigger : skeleton

    The recommended weight of LORA is around 0.6

    It is suitable for simple prompt words, model layout, realistic model or two-dimensional animation. The twomodels used in the example pictures are these two: Dream_and_Daily 梦与日常, Dream_and_Fantasy 梦与幻想. Can also be paired with other similar models.

    The sample diagram has complete parameters! Everyone is welcome to try it!Welcome to return pictures! Thanks.

    My common parameters

    Sampler: DPM++3M SDE Karras
    
    Number of steps: 30
    
    Hire Upgrader: R-ESRGAN 4x+
    
    Denoise intensity: 0.5,
    
    Clip skipped: 2,
    
    Hire upscale: 2,
    
    Hire steps: 20,

    【模型介绍及参数建议】

    可以产出骨架身体~ (显而易见)

    触发词是:skeleton 骨架

    LORA 权重 建议是0.6左右

    适用于简单的提示词,大模型搭配写实模型或二次元动漫都可以。

    例图用到的大模型是这两个:Dream_and_Daily 梦与日常Dream_and_Fantasy 梦与幻想

    也可以搭配其他大模型。

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

    例图上都有完整参数!欢迎大家尝试!

    欢迎返图!感谢。

    还是在这里放上我例图用了最多的参数

    尺寸:512x768 (为了速度我一般只开这么大,然后开高清修复)

    Sampler:DPM++3M SDE Karras      

    Steps:30

    Hires upscaler: R-ESRGAN 4x+

    Denoising strength: 0.5,

    Clip skip: 2,

    Hires upscale: 2,

    Hires steps: 20,

    欢迎感兴趣的朋友一起学习交流,VX:xat_0313 、XHS:嚣思_Rylee

    Description

    FAQ

    Comments (6)

    PeterAureliusOct 8, 2023
    CivitAI

    大佬你好,我想请教一下,这种lora是如何训练出来的,在训练集部分,是用只有头部的图片和只有身体骷髅的图片来训练的吗,谢谢

    Rylee
    Author
    Oct 9, 2023

    全身、半身都有

    PeterAureliusOct 10, 2023

    @XS_Rylee 你的意思是说,在训练集中,每张放入的图片都包括人头和骷髅身体吗,还是说会把人头和骷髅身体放在不同的图片里面,谢谢!

    Rylee
    Author
    Oct 19, 2023

    @PeterAurelius 部分训练图是经过合成的,人脸+骷髅 让AI识别这样的组合

    PeterAureliusOct 20, 2023

    @XS_Rylee 好的感谢,受教了

    snakeixDec 23, 2023
    CivitAI

    i like it a lot , well done man

    LORA
    SD 1.5

    Details

    Downloads
    853
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/20/2023
    Updated
    5/11/2026
    Deleted
    -
    Trigger Words:
    skeleton

    Files

    WanGu3.safetensors

    Mirrors

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