中文 | English
仿優子鈴的作画风格的LoRA模型。透明水彩风格。
使用时考虑添加这几个词条:watercolor_\(medium\), colored_pencil_\(medium\), marker_\(medium\), painting_\(medium\)
LoRA model imitating 優子鈴's painting style. Transparent watercolor style.
When using, consider adding these terms: watercolor_\(medium\), colored_pencil_\(medium\), marker_\(medium\), painting_\(medium\)
有用的提示:/ Helpful tip:
如果遇到看不出LoRA画风的情况,请考虑更换Checkpoint模型,尤其是一些自带强烈风格的Checkpoint模型。如果出图相当不稳定,也应该考虑更换Checkpoint模型。
If you encounter a situation where the LoRA style cannot be recognized, please consider changing the checkpoint model, especially for some checkpoint models with strong styles. If the output images are quite unstable, you should also consider changing the checkpoint model.
权重建议值:1 (or 0.6~1.4)
基于模型:Anything-5RE
训练信息:筛选出共计278张原画(含裁剪图),迭代1112步,多分辨率智能定向迭代训练。
其他的一些建议:EasyNegative,badhandv4,CreationMix。
Recommended weight value: 1 (or 0.6~1.4)
Based on model: Anything-5RE
Training information: Selected a total of 278 original drawings (including cropped images), iterated 1112 steps, and trained with multi-resolution intelligent directional iteration.
Other suggestions: EasyNegative, badhandv4, CreationMix.