<h1 id="heading-4318">へら Style LoRA</h1>中文 | English--<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3366fab9-105a-4e69-9aa9-dec187f8c3f7/width=525/3366fab9-105a-4e69-9aa9-dec187f8c3f7.jpeg" /><a target="_blank" rel="ugc" href="https://o365cn1-my.sharepoint.com/personal/cdn-cn_o365cn1_onmicrosoft_com/_layouts/52/download.aspx?share=EcDEncZ4qE1NrTK3hDQHyTIB19BDJtqwUoXp0BSwXqVgWw">https://o365cn1-my.sharepoint.com/personal/cdn-cn_o365cn1_onmicrosoft_com/_layouts/52/download.aspx?share=EcDEncZ4qE1NrTK3hDQHyTIB19BDJtqwUoXp0BSwXqVgWw</a>--主要针对技法进行训练，生成角色需另找模型。Mainly for the training of painting techniques, to generate corresponding characters need to find other models.--仿へら的作画风格的LoRA模型。权重建议值：1 (or 0.5~1.4)基于模型：Anything-5RE训练信息：共计548张原画(含裁剪图)，迭代约4000步。拟合比率：<ul><li>肢体拟合：9%</li><li>人物拟合：48%</li><li>构图拟合：21%</li><li>技法拟合：116%</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。--A LoRA model that mimics the painting style of Hara.Recommended weight value: 1 (or 0.5~1.4)Based on model: Anything-5RETraining information: A total of 548 paintings (including cropped images) with about 4000 iterations.Fitting ratio:<ul><li>Motion fitting: 9%</li><li>Character fitting: 48%</li><li>Composition fitting: 21%</li><li>Technique fitting: 116%</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: 98903d0125ed3b3cc5662ae749ef47434cfc7b44ff04108dce688752e7728eed