简体中文 | English
--
仿TID画师的作画风格的LoRA模型,其画风端庄大方得体。
权重建议值:1 (or 0.5~1.2)
基于模型:Anything-5RE
训练信息:共计300张原画(含裁剪图),迭代916步。
拟合比率:
肢体拟合:90%(原本是打算抹掉动作的,后面发现差了些意思,干脆走还原向)
人物拟合:95%
构图拟合:105%
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 TID's painting style, which is elegant and refined.
Recommended weight value: 1 (or 0.5~1.2)
Based on model: Anything-5RE
Training information: A total of 300 paintings (including cropped images) with 916 iterations.
Fitting ratio:
Motion fitting: 90% (Originally intended to erase the motion, but later discovered that it missed some meaning, so I decided to go for restoration)
Character fitting: 95%
Composition fitting: 105%
Technique fitting: 115%
Other recommendations: EasyNegative, badhandv4. Moreover, in case of distorted limbs, try starting over with a different seed.
--
未测试与其他模型兼容性,不过跟V家的虚拟歌姬应该很合适。
Compatibility with other models has not been tested, but it should be suitable for use with virtual songstress.
--
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.