<h1 id="mansui-anima-lora">这是哀鸿城破十日记里的满穗（Mansui）的 Anima 角色 LoRA，</h1><h3 id="anima-lora-0.80-lora-v1.1v1.0">建议使用兼容 Anima 的底模，并将人物 LoRA 权重从 <code>0.80</code> 开始测试。强风格 LoRA 叠加过高时，可能会改变脸型、眼睛比例、发饰和服装细节。 V1.1更贴合原设定 V1.0解绑更自由</h3><h2>使用方法</h2>基础示例：<pre><code>1girl, mansui, solo, grey eyes, black hair, long hair, side bun, hair ornament, looking at viewer</code></pre>原设服饰示例：<pre><code>1girl, mansui, solo, grey eyes, black hair, long hair, side bun, hair ornament, chinese clothes, hanfu, grey robe, white skirt, wide sleeves, full body</code></pre>现代换装示例：<pre><code>1girl, mansui, solo, grey eyes, black hair, long hair, ponytail, white shirt, beige apron, dark skirt, flower shop</code></pre>推荐负面提示词：<pre><code>huge eyes, oversized eyes, chibi, child, bad anatomy, extra fingers, malformed hands, blurry, watermark, text, signature</code></pre><h3> 使用说明</h3>本模型主要用于 AI 绘图测试、角色还原、学习交流及非商业同人创作。请在合理、合法的范围内使用，并尊重原作品及相关创作者的权益。<h2>免责声明</h2>本 LoRA 为非官方同人模型，与原作者、画师、开发商、发行方及版权方均无任何官方关联。模型涉及的角色形象、原作设定、美术素材及相关知识产权均归各自权利方所有。上传者仅进行了个人兴趣性质的模型训练与分享，不主张对原角色或原作品拥有任何权利。请勿使用本模型冒充官方内容、进行虚假署名、误导性宣传，或从事可能损害原作者及相关权利方权益的行为。如原作者、版权方或其他相关权利人对本模型的发布存在异议，可以联系我，我会认真处理相关问题。<hr />This is a fan-made and unofficial LoRA model, mainly created for AI image generation experiments, learning, and fan works.I do not own the original character, artwork, source material, or any related intellectual property. All rights belong to their respective owners. This model is not affiliated with, endorsed by, or officially connected to the original creators, artists, publishers, developers, or copyright holders.Please do not use this LoRA to impersonate official artwork, falsely claim authorship, mislead others, or infringe upon the rights of the original creators.This model is mainly trained for character likeness. Because of the training dataset, certain outfits, poses, expressions, or background elements may appear more frequently than expected. If the character looks too fixed or the LoRA has too much influence on the image, try lowering the LoRA weight.I am still learning LoRA training, so the model may not be perfect. Feedback, suggestions, testing results, and example images are always welcome.

满穗 / Mansui

满穗（Mansui）｜V1.1版本这是满穗（Mansui）Anima 角色 LoRA 的 EP16 checkpoint。相比 EP14，本版本继续训练了 2 个 epoch，身份特征绑定更强，黑发、灰色眼睛、长发、侧发髻和发饰的稳定性略有提升。适合希望角色特征更明确的场景。触发词： <code>mansui</code>推荐 LoRA 权重： <code>0.80</code>建议测试范围： <code>0.70–0.80</code>适用底模： Anima / anima-base-v1.0本版本来自 24 epoch 训练过程，训练集 75 张，正则集 75 张，Rank / Alpha 为 64 / 64，训练分辨率为 1024。相比 EP14，EP16 的身份绑定更明显，但在强风格 LoRA 或复杂换装场景下，服装和发饰可能更容易受到绑定影响。建议根据画面需要在 0.70–0.80 之间调整权重。

Files with SHA256: c978f4d345aef2082ccee001ed9561c06c7f32ada8c8c99f0d817a76b935dd55