Type | |
Stats | 1,724 |
Reviews | (324) |
Published | Jul 26, 2023 |
Base Model | |
Training | Steps: 1,100 Epochs: 1 |
Usage Tips | Clip Skip: 2 |
Hash | AutoV2 B302F305BA |
Animi Style LoRA
简体中文 | English 使用前阅读 | Read before use
--
--
仿Animi的作画风格的LoRA模型。
权重建议值:0.8 or 1.0
基于模型:Anything-5RE
训练信息:共计192张原画(含裁剪图),迭代约1100步。
拟合比率:
肢体拟合:40%
人物拟合:98%
构图拟合:23%
技法拟合:117%
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 Animi's painting style.
Recommended weight value: 0.8 or 1.0
Based on model: Anything-5RE
Training information: A total of 192 paintings (including cropped images) with about 1100 iterations.
Fitting ratio:
Motion fitting: 40%
Character fitting: 98%
Composition fitting: 23%
Technique fitting: 117%
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.