<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>StableDiffusion - 标签 - 研发日志 · R&amp;D Log</title><link>https://rd163.visword.com/tags/stablediffusion/</link><description>StableDiffusion - 标签 - 研发日志 · R&amp;D Log</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><managingEditor>whutluohui@gmail.com (小智晖)</managingEditor><webMaster>whutluohui@gmail.com (小智晖)</webMaster><copyright>本作品采用知识共享署名-非商业性使用 4.0 国际许可协议进行许可。</copyright><lastBuildDate>Mon, 10 Mar 2025 00:00:00 +0800</lastBuildDate><atom:link href="https://rd163.visword.com/tags/stablediffusion/" rel="self" type="application/rss+xml"/><item><title>ComfyUI教程</title><link>https://rd163.visword.com/posts/comfyui-get-started/</link><pubDate>Mon, 10 Mar 2025 00:00:00 +0800</pubDate><author><name>小智晖</name></author><guid>https://rd163.visword.com/posts/comfyui-get-started/</guid><description><![CDATA[<h2 id="术语解释" class="headerLink">
    <a href="#%e6%9c%af%e8%af%ad%e8%a7%a3%e9%87%8a" class="header-mark"></a>术语解释</h2><ul>
<li>VAE:变分自动编码器（Variational Autoencoder）,负责图像在像素空间与潜空间之间的转换。</li>
<li>CLIP 模型：全称 Contrastive Language-Image Pre-Training(对比式语言-图像预训练模型),用于将文本编码为模型可理解的特征。</li>
<li>T5:Google 提出的文本编码器，FLUX 等模型用它来理解更复杂、更长的提示词。</li>
</ul>
<h2 id="安装" class="headerLink">
    <a href="#%e5%ae%89%e8%a3%85" class="header-mark"></a>安装</h2><p>参考 GitHub 官方仓库，直接下载桌面安装包:</p>]]></description></item></channel></rss>