<h3 id="if-you-have-the-means-please-do-support-the-original-artist's-creative-work!">⭐ If you have the means, please do support the original artist's creative work! <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">⭐如果各位有能力的话，请务必支持原画师的创作工作！</h3>This LoRa was trained using the public works of <a target="_blank" rel="ugc" href="https://x.com/NlzjF">おきたつき (Okitatsuki)</a> as material distillation, aiming to achieve a realistic skin texture for anime characters. I recommend using it in conjunction with other anime-style/3D-style LoRa for better performance.Strength: 0.6-1.0 When used in conjunction with other LoRA devices, I recommend using a strength below 0.8. 使用了 <a target="_blank" rel="ugc" href="https://x.com/NlzjF">おきたつき（Okitatsuki）</a>的公开作品作为素材蒸馏训练出来的LoRA，目的是为了实现动漫角色拥有真实皮肤质感。建议配合其他其他二次元风格/3D风格LoRA一起使用，获得更佳的使用效果。 强度：0.6-1.0，混合其他LoRA时推荐0.8以下。样例图的后两张为混合其他LoRA后生成的图像！详见这个LoRA的推荐表列。 The last two images in the sample gallery are generated by mixing with other LoRA images! Please refer to the Suggested Resources list of this LoRA for details. If you find that natural language as a prompt always results in realistic-style characters, you can try using pure tags as prompts (just like Anima), or like me, preface the prompt with the following content:<code>一张超清画质、二次元角色高精度插画图像</code> 如果你发现自然语言作为提示词老是出现真实风格角色，你可以尝试纯tag作为提示词（就像Anima一样），或者像我一样在提示词开头放上以下内容： <code>一张超清画质、二次元角色高精度插画图像</code>

Files with SHA256: 39fc582b7fe534324aa2168d267cc0f51c4d8a9d9e2789ae604be771618b78e2