へら Style LoRA
中文 | English
--
--
主要针对技法进行训练，生成角色需另找模型。
Mainly for the training of painting techniques, to generate corresponding characters need to find other models.
--
仿へら的作画风格的LoRA模型。
权重建议值：1 (or 0.5~1.4)
基于模型：Anything-5RE
训练信息：共计548张原画(含裁剪图)，迭代约4000步。
拟合比率：
肢体拟合：9%
人物拟合：48%
构图拟合：21%
技法拟合：116%
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。
--
A LoRA model that mimics the painting style of Hara.
Recommended weight value: 1 (or 0.5~1.4)
Based on model: Anything-5RE
Training information: A total of 548 paintings (including cropped images) with about 4000 iterations.
Fitting ratio:
Motion fitting: 9%
Character fitting: 48%
Composition fitting: 21%
Technique fitting: 116%
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.
Description
First version.