<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Gradio on TPOW Lab</title><link>https://tpow-001.netlify.app/tags/gradio/</link><description>Recent content in Gradio on TPOW Lab</description><generator>Hugo</generator><language>en</language><copyright>Copyright &amp;copy; 2025-2026 TPOW-001. All Rights Reserved.</copyright><lastBuildDate>Tue, 02 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://tpow-001.netlify.app/tags/gradio/index.xml" rel="self" type="application/rss+xml"/><item><title>Tutorial: OpenBMB/VoxCPM — Tokenizer-Free Diffusion AR TTS 完整解讀（VoxCPM 2 / 1.5 / 0.5B、Voice Cloning / Design、LoRA 微調、生態系）</title><link>https://tpow-001.netlify.app/post/2026-06-02-voxcpm-tutorial/</link><pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate><guid>https://tpow-001.netlify.app/post/2026-06-02-voxcpm-tutorial/</guid><description><![CDATA[<h1 id="voxcpm-完整教學" data-numberify>VoxCPM 完整教學<a class="anchor ms-1" href="#voxcpm-完整教學"></a></h1>
<blockquote>
<p><strong>一句話定位</strong>：OpenBMB（清華大學 NLP / 面壁智能 ModelBest 主導）旗下旗艦 <strong>TTS (text-to-speech; 文字轉語音)</strong> 開源項目；採 <strong>tokenizer-free + diffusion autoregressive</strong> 架構、基於 <strong>MiniCPM-4 language model</strong> + <strong>AudioVAE V2 latent space</strong>，最新版 <strong>VoxCPM 2</strong> 以 2B 參數支援 <strong>30 種語言</strong>、<strong>48 kHz</strong> 高保真合成、<strong>voice design</strong>（純文字描述生聲）、<strong>voice cloning</strong>（參考音複製）、<strong>controllable cloning</strong>（風格調整）、<strong>streaming</strong>，Apache-2.0 可商用。</p>]]></description></item><item><title>Stable Diffusion WebUI (A1111) 詳細教學</title><link>https://tpow-001.netlify.app/post/2026-05-22-sd-webui-tutorial/</link><pubDate>Fri, 22 May 2026 00:00:00 +0000</pubDate><guid>https://tpow-001.netlify.app/post/2026-05-22-sd-webui-tutorial/</guid><description><![CDATA[<h1 id="stable-diffusion-webui-a1111-詳細教學" data-numberify>Stable Diffusion WebUI (A1111) 詳細教學<a class="anchor ms-1" href="#stable-diffusion-webui-a1111-詳細教學"></a></h1>

<h2 id="1-專案定位與適用情境" data-numberify>§1. 專案定位與適用情境<a class="anchor ms-1" href="#1-專案定位與適用情境"></a></h2>
<p><code>stable-diffusion-webui</code> (常稱 A1111 / WebUI) 是 stable diffusion (SD; 穩定擴散) 模型的本地圖形化操作介面，以 gradio (Gradio; 一個快速 web UI 框架) 為前端、PyTorch 為後端推論引擎。</p>]]></description></item></channel></rss>