AI净土交流群电报：https://t.me/+soU-Ws67aBlkY2I1

凯登AI私模定制咨询电报：https://t.me/+Ql4sngcJlbhmOTU1

Trigger Words : dunhuang

触发词 : dunhuang

V3版说明：

1. 优化服饰一致性，整体画风更加统一清晰

2. 构图更稳定，不易出现手足扭曲等问题

3. 服饰表现更加自然流畅

4. 更好地兼容动画模型与真人模型

总体而言，生成高质量作品的难度降低，效果更佳

Version V3 description:

1. Modify the consistency of clothing, and the overall painting style is no longer tangled
2. Composition is not easy to break hands and feet
3. Dress more naturally
4. Better compatibility between animated models and real models
   It's easier to produce beautiful work in general

加入上百种敦煌风格服饰，降低脸部权重，更好与lora搭配！

服装分层数据：

CLOTHING:1,1,1,1,1,0,0.2,0,0.8,1,1,0.2,0,0,0,0,0

注意：示例图片中并未对人物手部、姿态和表情进行调节，展示图片也并非精心挑选，而是随机生成并展示部分服饰效果

This version adds over a hundred Dunhuang style clothing styles to reduce facial weight and better match Lora!

Note: The example images did not adjust the hands, posture, and expressions of the characters, and the display images were not carefully selected. Instead, several clothing effects were randomly generated and displayed

V2.1版本

一些示例：

（由于舞蹈动作中手部和肢体特征复杂，常出现崩坏，案例图片我懒得修复了）

仅保留人物服饰特征，去除背景：

lora:dunhuangV2.1:1:1,1,1,1,0,0,1,1,1,1,1,1,1,0,0,1,1

以下是去除敦煌风格背景后，重新绘制背景的效果