<h3 id="heading-13">请注意：</h3><ol><li>我常用的CFG范围是6~7，Lora权重通常在0.5~0.7。</li><li>Clip skip设为1或2时，生成的效果会有所不同，大家可以多尝试看自己喜欢哪种风格。</li></ol>Please note:<ol><li>My commonly used CFG range is 6 to 7, and the Lora weight is usually 0.5 to 0.7.</li><li>When the Clip skip is set to 1 or 2, the generated effects will be different. You can try more to see which style you like.</li></ol>VELVIA模型是采用高分辨率训练集以及新的打tag方法训练得到的LoRA模型。更新内容：<ul><li>照片训练集进行了重新筛选，不再使用正则化图像</li><li>训练集分辨率由512x704提升至640x960</li><li>采用了新的打tag方法与金字塔噪声</li></ul>The VELVIA model is a LoRA model trained using a high-resolution dataset and a new tagging method.Updates include:<ul><li>The photo training dataset has been reselected, no longer using regularized images.</li><li>The training dataset's resolution has been increased from 512x704 to 640x960.</li><li>A new tagging method and pyramid noise has been adopted.</li></ul><ul><li>英语：Layered control processing has been carried out. Now it can be used in any model, any weight, any style, and it will not affect other clothes.</li><li>中文：已进行分层控制处理，现在可以在任何模型、任何权重、任何风格中使用，并且不会影响其他衣服。</li><li>日语：レイヤー制御処理が行われています。これでどのモデルでも、どの重さでも、どのスタイルでも使用することができ、他の服に影響を与えません。</li><li>韩语：계층화된 제어 처리가 이루어졌습니다. 이제 어떤 모델이든, 어떤 무게든, 어떤 스타일이든 사용할 수 있으며, 다른 옷에는 영향을 미치지 않습니다.</li></ul>欢迎关注： 有问题可以直接平台私信

Files with SHA256: c767a0886d774adcef84b64abdb44ba831949835e61bd0366dd9a55e3b26da66