<a target="_blank" rel="ugc" href="https://ko-fi.com/zyd232">Buy me a coffee ☕</a><ul><li>I suggest you set the LoRA weight from 0.8 to 1.2. It depends on the model and the prompt you use.</li><li>Theoretically, you can use it with any models based on SD 1.5.</li><li>For some models, it's better to add all the trigger words to the prompt if necessary.</li><li>To generate better images, please use Hi-Res.</li><li>Use Euler a as the sampler to get more delicate images.</li></ul>　The negative prompt in example images has something wrong: the second half of the negative tags is duplicated with the prompt tags.Just ignore it. (The problem is caused by an extension.)　You are welcome to share your pics generated with this LORA. But please keep those extremely NSFW ones to yourself.　-　<ul><li>推荐的 LoRA 权重为 0.8到1.2，具体数值取决于你的底模和提示词。</li><li>理论上，任何基于SD 1.5而炼成的模型都可以与这个LORA兼容。</li><li>对于某些底模，有需要时，最好把 所有的触发词 都加上。</li><li>为了生成更好的图片，请使用高清修复功能。</li><li>使用 Euler a 作为采样器，可以获得更细腻平滑的图片。</li></ul>　示例图片中的负面提示词有些问题：负面提示词后半部分的内容和提示词重复了。请无视。（这个问题是由于我用的某个插件造成的。）　欢迎在评论区分享你用这个LORA生成的图片。但是请不要分享过于暴露的内容。

Files with SHA256: fd213f711533ab00c04a81cca50652fa93381f312169a92bd38e6b563662054c