TOKKYU Style LORA V2

简体中文 | English 使用前阅读 | Read before use

--

仿TOKKYU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686张原画(含裁剪图)，迭代1,066步。

拟合比率：

• 肢体拟合：13%

• 人物拟合：82%

• 构图拟合：35%

• 技法拟合：115%

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 mimics TOKKYU's painting style.

Recommended weight value: 1 (or 0.5~1.2)

Based on model: Anything-5RE

Training information: A total of 686 paintings (including cropped images) with 1066 iterations.

Fitting ratio:

• Motion fitting: 13%

• Character fitting: 82%

• Composition fitting: 35%

• Technique fitting: 115%

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.