Artist: ゆさの/yusano
详情
下载文件
关于此版本
模型描述
ゆさの 的风格 LoRA
中文 | English
--

--
请自行提供人物模型。主要针对绘画技法进行训练。当四肢出现异常时,请降低模型权重。
Bring your own character model. Mainly for the training of painting techniques. Lower model weights when limbs are problematic.
--
模仿ゆさの绘画风格的 LoRA 模型。
推荐权重值:0.8(或 0.5~1.2)
The LoRA model mimics yusano's painting style.
Recommended weight value: 0.8 (or 0.5~1.2)
--
训练相关/About training:
训练集共包含 6 张图片。采用双向差异法 + 多模型蒸馏。
This version of the model uses bidirectional difference method + multi-model distillation. The training set consists of a total of 6 images.
loss rate < 1%
--
如有任何问题,欢迎反馈,不提出问题就无法得到解决。
Any questions are welcome for feedback, as problems will not be solved without being raised.







