My English is not very good, there may be some translation problems, please forgive me.<h3 id="heading-1343">I have created another very small model, if anyone likes it I will continue to optimize it.</h3>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。-------------------------------------------------------------------------------------------------<h2 id="heading-1344">[Model introduction and parameter recommendations]</h2><h2 id="heading-1345">trigger : skeleton </h2><h3 id="heading-1346">The recommended weight of LORA is around 0.6</h3>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: <a rel="ugc" href="https://civarchive.com/models/136006/dreamanddaily">Dream_and_Daily 梦与日常</a>, <a rel="ugc" href="https://civarchive.com/models/130449/dreamandfantasy">Dream_and_Fantasy 梦与幻想</a>. 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.<h3 id="heading-1347">My common parameters</h3><pre><code>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,</code></pre><h2 id="heading-1348">【模型介绍及参数建议】</h2>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：<a rel="ugc" href="https://civarchive.com/models/136006/dreamanddaily">Dream_and_Daily 梦与日常</a>、<a rel="ugc" href="https://civarchive.com/models/130449/dreamandfantasy">Dream_and_Fantasy 梦与幻想</a>。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:30Hires 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

玩骨 WanGu

WanGu3.safetensors

v1.0

Play Bone WangU

I'm on a very niche model again, and if anyone likes it, I'll continue to optimize it. First of all, thanks to @遇见清风 for providing the materials and creating with me. ----------------------------------------------------------------- [Model introduction and parameter suggestions] Can produce a skeletal body~ ( (Obvious) The trigger word is: skeleton skeleton The weight recommendation for LORA is around 0.6, which is suitable for simple hints. Large models can be paired with realistic models or two-dimensional animations. The large models used in the example are these two: dreams and everyday life, and dreams and fantasies. Because of a website problem, I didn't post a link. You can search directly or use it with other big models. ----------------- All the parameters are complete on the example image! Everyone is welcome to try it! Welcome back to the picture! Thanks. Here is the size of the parameter I used the most in my example image: 512x768 (I usually only drive this big for speed, then turn on HD repair) 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,

Files with SHA256: 8d52d14265429d293b5fa2a361f4e5d77ec0b7f0a80a22c244cc9818f600ced3