
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.
描述:
First version
训练词语: 1girl
名称: style_TOKKYU.safetensors
大小 (KB): 37008
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success