<h1 id="heading-66">純白可憐 Style LoRA V2</h1>中文 | English--<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/28f2076b-8051-4b06-839f-ef71d8b72b58/width=525/28f2076b-8051-4b06-839f-ef71d8b72b58.jpeg" /><a target="_blank" rel="ugc" href="https://o365cn1-my.sharepoint.com/personal/cdn-cn_o365cn1_onmicrosoft_com/_layouts/52/download.aspx?share=Ea5qQ1qT5P1JiXjBYkjKfhAB0vQ9ZZVJYWqbYuY8aY2Vgg">https://o365cn1-my.sharepoint.com/personal/cdn-cn_o365cn1_onmicrosoft_com/_layouts/52/download.aspx?share=Ea5qQ1qT5P1JiXjBYkjKfhAB0vQ9ZZVJYWqbYuY8aY2Vgg</a>--典型：1girl, looking_at_viewer, jewelry, chinese clothes, floating hair, long hair, east asian architectureTypical: 1girl, looking_at_viewer, jewelry, chinese clothes, floating hair, long hair, east asian architecture--仿纯白可怜的作画风格的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300张原画(含裁剪图)，迭代约1400步。拟合比率：<ul><li>肢体拟合：10%</li><li>人物拟合：82%</li><li>构图拟合：24%</li><li>技法拟合：108%</li></ul>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 imitates the painting style of Pale.Recommended weight value: 1 (or 0.5~1.2)Based on model: Anything-5RETraining information: A total of 300 paintings (including cropped images) with about 1400 iterations.Fitting ratio:<ul><li>Motion fitting: 10%</li><li>Character fitting: 82%</li><li>Composition fitting: 24%</li><li>Technique fitting: 108%</li></ul>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.

Files with SHA256: d3e484bf83df1500d39ac387b0d62de0157551247d647be3cc39694511e3146c