純白可憐 Style LoRA V2

中文 | English

--

https://o365cn1-my.sharepoint.com/personal/cdn-cn_o365cn1_onmicrosoft_com/_layouts/52/download.aspx?share=Ea5qQ1qT5P1JiXjBYkjKfhAB0vQ9ZZVJYWqbYuY8aY2Vgg

--

典型：1girl, looking_at_viewer, jewelry, chinese clothes, floating hair, long hair, east asian architecture

Typical: 1girl, looking_at_viewer, jewelry, chinese clothes, floating hair, long hair, east asian architecture

--

仿纯白可怜的作画风格的LoRA模型。

权重建议值：1 (or 0.5~1.2)

基于模型：Anything-5RE

训练信息：共计300张原画(含裁剪图)，迭代约1400步。

拟合比率：

• 肢体拟合：10%

• 人物拟合：82%

• 构图拟合：24%

• 技法拟合：108%

其他的一些建议：EasyNegative, badhandv4。此外，万一畸形四肢换个种子重画就行。

--

The LoRA model imitates the painting style of Pale.

Recommended weight value: 1 (or 0.5~1.2)

Based on model: Anything-5RE

Training information: A total of 300 paintings (including cropped images) with about 1400 iterations.

Fitting ratio:

• Motion fitting: 10%

• Character fitting: 82%

• Composition fitting: 24%

• Technique fitting: 108%

Other recommendations: EasyNegative, badhandv4. Moreover, in case of distorted limbs, try starting over with a different seed.

--

任何问题，欢迎反馈，问题不提出就不会得到解决。如果你创作出了好作品，欢迎分享它。如果它无法满足你的需求，我是说，我的朋友，请不要给出一星好评。

Any questions are welcome for feedback, as problems will not be solved without being raised. If you have created a great work, please feel free to share it. If it cannot meet your needs, my friend, please do not give a one-star rating.