
美和野 Style LoRA V2
中文 | English
--
--
仿美和野的作画风格的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264张原画(含裁剪图),迭代约2100步,
拟合比率:
-
肢体拟合:28%
-
人物拟合:91%
-
构图拟合:38%
-
技法拟合:109%
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 MiwanoRag.
Recommended weight value: 1 (or 0.5~1.2)
Based on model: Anything-5RE
Training information: A total of 264 paintings (including cropped images) with about 2100 iterations.
Fitting ratio:
-
Motion fitting: 28%
-
Character fitting: 91%
-
Composition fitting: 38%
-
Technique fitting: 109%
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.
描述:
First version.
训练词语: 1girl
名称: style_MiwanoRag.safetensors
大小 (KB): 37075
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success