Type | |
Stats | 2,357 |
Reviews | (304) |
Published | Aug 14, 2023 |
Base Model | |
Training | Steps: 1,200 |
Usage Tips | Clip Skip: 2 |
Hash | AutoV2 A8A8FD054D |
きょくちょStyle LoRA V3
简体中文 | English
--
--
✅R18
✅黑白画面 / Monochrome
--
仿局长的作画风格的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166张原画(含裁剪图),迭代约1200步。
拟合比率:
肢体拟合:16%
人物拟合:103%
构图拟合:29%
技法拟合:112%
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 Kiyokujiyo's painting style!!
Recommended weight value: 1 (or 0.5~1.2)
Based on model: Anything-5RE
Training information: A total of 166 paintings (including cropped images) with about 1200 iterations.
Fitting ratio:
Motion fitting: 16%
Character fitting: 103%
Composition fitting: 29%
Technique fitting: 112%
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.
--