玉之けだま Style LoRA V3
简体中文 | English 使用前阅读 | Read before use
--
--
典型：1girl, two side up, small breasts, ribbon, cowboy shot
Typical: 1girl, two side up, small breasts, ribbon, cowboy shot
图放不了再多，已经被下架一回了，自行尝试吧。
--
仿玉之けだま的作画风格的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396张原画(含裁剪图)，迭代约2000步。
拟合比率：
肢体拟合：23%
人物拟合：95%
构图拟合：28%
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。
--
The LoRA model mimics Kedamaa's painting style.
Recommended weight value: 1 (or 0.5~1.2)
Based on model: Anything-5RE
Training information: A total of 396 paintings (including cropped images) with about 2000 iterations.
Fitting ratio:
Motion fitting: 23%
Character fitting: 95%
Composition fitting: 28%
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.