closed2open / multimodal.html
abidlabs's picture
abidlabs HF Staff
changes
afb9f5f
raw
history blame
1.71 kB
<!doctype html>
<html>
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width" />
<title>Multimodal - ClosedToOpen</title>
<link rel="stylesheet" href="style.css" />
</head>
<body>
<nav class="navbar">
<div class="nav-content">
<h1 class="nav-title">ClosedToOpen</h1>
<p class="nav-subtitle">how to stop relying on proprietary APIs for AI and start living freely</p>
</div>
</nav>
<main class="main-content">
<div class="breadcrumb">
<a href="index.html">← Back to Topics</a>
</div>
<section class="topic-header">
<h1 class="topic-title">Multimodal</h1>
<p class="topic-description">Process images, audio, and video with open-source multimodal models</p>
</section>
<section class="recipes-section">
<h2 class="section-title">Recipes</h2>
<div class="recipes-grid">
<div class="recipe-card">
<h3>GPT-4V β†’ LLaVA</h3>
<p>Replace GPT-4V with LLaVA for image understanding tasks</p>
<div class="recipe-status">Coming Soon</div>
</div>
<div class="recipe-card">
<h3>DALL-E β†’ Stable Diffusion</h3>
<p>Generate images using Stable Diffusion instead of DALL-E</p>
<div class="recipe-status">Coming Soon</div>
</div>
<div class="recipe-card">
<h3>Whisper β†’ Whisper.cpp</h3>
<p>Use local Whisper implementation for speech-to-text</p>
<div class="recipe-status">Coming Soon</div>
</div>
<div class="recipe-card">
<h3>Video Understanding</h3>
<p>Process video content with open-source video models</p>
<div class="recipe-status">Coming Soon</div>
</div>
</div>
</section>
</main>
</body>
</html>