AI

Follow me to make sure you see new styles, poses and Nobodys when I post them. Things move fast on t

可以配合下方推荐的其他图像调整LoRA一起使用。 【中文】 完全自由的亮度调节工具！ 几乎所有大模型都可以用 推荐权重：-2.0~2.0，权重越大，图片亮度就越高。负数就是降低亮度 【English】

This is a tool that I train to change the style and eye colors of my generated characters. I use the

当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 SDK下载 #安装ModelS

[**_You can join my discord server here!_**](https://discord.gg/zYdmcWgqaP) You can also find me on

Shinkawa Youji style LoRA Making models can be expensive. Do you like what I do? Consider supporting

2023/3/31 update Fix the compatibility problem of non-NAI-based checkpoints. Now arbitrary anime mod

If you want to know the story of these monsters, please read I wrote the background and my review i

also: if it does not work for you download the training data aka model.zip and choose an earlier ver

结合https://civitai.com/models/38511?modelVersionId=44457 的DDicon模型使用，生成玻璃质感web风格B端元素。 v1和v2版本建议对应使用，v

? New Discord, come play with us: https://discord.gg/rHCnjX9cW9 Introducing Elixir ? — a LoRA that

Trained on NAI with 235 images this LoRA is capable of convincingly reproduce Ochako. The triggerwor

这不能算是一个正式的版本，因为它不够稳定，达不到我的预期。 在过去的几天里我都在制作这个Lora，废弃了很多个版本，总是不能得到令我满意的结果，它实在是很难控制，跟AI稳定生成手一样困难。这个发布的版

i know some models already have a good glass sculpture support, but many others, just don't, this is

注意：我的模型经过 locon 训练，所以需要安装LoCon 支持。 https://github.com/KohakuBlueleaf/a1111-sd-webui- locon ** PS：有好点

You can also download a full-merged model here (just in case you don't have Anything V4.5 or want to

"AI-Game Icon Institute" 推荐使用大模型配合使用 **Here is the link to the method of correctly using th

Hyouka (Kyoto Animation / Kyoani) style LoRA Making models can be expensive. Do you like what I do?

When using this LoRA, it may be a better image to redraw only face or eyes using inpaint. Or, it is

Weight 0.8~1.0 ,and you can ADJUST prompt to reductive character You can trigger different** THREE**