QuAn Avatar Art Style LoRA

Art style of QuAn(泉酱, 也可以叫QuAn_, QuAn___ or __QuAn_ 什么下划线排列组合).

This model is trained base on Anything 4.5 model and 640X640 resolution.

Trigger word avatar is not required, it can make face larger, 但更容易出现一些奇奇怪怪的背景元素。

Common uses: simple background , upper body , smile , open mouth or closed mouth

Versions

v2 includes two model, quan_style_v2 and quan_style_v2-avatar .

quan_style_v2-avatar is specialized for making avatars, but more likely to generate artist's signature in the corner.

我去除了训练集中大部分的无用的元素，但是我保留了签名部分，我觉得保留了一部分，才知道你生成的是泉酱风格的头像

Block Weights

If you use sd-webui-lora-block-weight plugin, you can specify weights to affect results.

The style preset is 1,0,0.5,0,0.5,1,1,1,1,1,1,0.5,0.5,0.5,0.5,0.5,0.5 , according to the block analyser.

This model has not received a license reply yet. If you believe that this model infringes on your rights, please contact me and I will take it down.