|
|
<!DOCTYPE html> |
|
|
<html lang="en"> |
|
|
<head> |
|
|
<meta charset="utf-8" /> |
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
|
|
<title>Wan 2.2 - Advanced Video Generation by Alibaba Tongyi Lab</title> |
|
|
<meta name="description" content="Wan 2.2: Open and Advanced Large-Scale Video Generative Models by Alibaba Tongyi Lab. Featuring MoE architecture, cinematic-level aesthetics, and complex motion generation." /> |
|
|
<meta name="keywords" content="Wan 2.2, Alibaba, Tongyi Lab, Video Generation, AI Models, Text-to-Video, Image-to-Video, WaveSpeedAI, MoE, Video AI" /> |
|
|
|
|
|
|
|
|
<meta property="og:title" content="Wan 2.2 - Advanced Video Generation by Alibaba Tongyi Lab" /> |
|
|
<meta property="og:description" content="Experience the next generation of video AI with Wan 2.2, developed by Alibaba Tongyi Lab" /> |
|
|
<meta property="og:type" content="website" /> |
|
|
<meta property="og:url" content="https://wavespeed.ai/collections/wan-2-2" /> |
|
|
|
|
|
|
|
|
<meta name="author" content="Alibaba Tongyi Lab" /> |
|
|
<meta name="robots" content="index, follow" /> |
|
|
<link rel="canonical" href="https://wavespeed.ai/collections/wan-2-2" /> |
|
|
|
|
|
<link rel="stylesheet" href="style.css" /> |
|
|
<meta http-equiv="refresh" content="10;url=https://wavespeed.ai/collections/wan-2-2" /> |
|
|
</head> |
|
|
<body> |
|
|
<nav class="top-nav"> |
|
|
<div class="nav-content"> |
|
|
<div class="nav-logo">WAN</div> |
|
|
<div class="nav-links"> |
|
|
<a href="https://wavespeed.ai/collections/wan-2-2" class="nav-link" target="_blank" rel="noopener noreferrer">Home</a> |
|
|
<a href="https://wavespeed.ai/docs" class="nav-link" target="_blank" rel="noopener noreferrer">Documentation</a> |
|
|
<a href="https://wavespeed.ai/blog" class="nav-link" target="_blank" rel="noopener noreferrer">Blog</a> |
|
|
<a href="https://wavespeed.ai/collections/wan-2-2" class="nav-button" target="_blank" rel="noopener noreferrer">Visit WaveSpeedAI →</a> |
|
|
</div> |
|
|
</div> |
|
|
</nav> |
|
|
|
|
|
<div class="container"> |
|
|
<div class="content"> |
|
|
<div class="logo-section"> |
|
|
<h1>Wan 2.2</h1> |
|
|
<p class="subtitle">By Alibaba Tongyi Lab</p> |
|
|
</div> |
|
|
|
|
|
<div class="announcement-section"> |
|
|
<p class="announcement">Wan 2.2 is now available on WaveSpeedAI!</p> |
|
|
<div class="divider"></div> |
|
|
<p class="description">Open and Advanced Large-Scale Video Generative Models</p> |
|
|
</div> |
|
|
|
|
|
<div class="features-section"> |
|
|
<div class="feature"> |
|
|
<h3>🚀 Effective MoE Architecture</h3> |
|
|
<p>Advanced Mixture-of-Experts architecture separates denoising process with specialized expert models, enlarging model capacity while maintaining computational cost</p> |
|
|
</div> |
|
|
<div class="feature"> |
|
|
<h3>🎯 Cinematic-level Aesthetics</h3> |
|
|
<p>Meticulously curated aesthetic data with detailed labels for lighting, composition, contrast, and color tone for precise and controllable cinematic style generation</p> |
|
|
</div> |
|
|
<div class="feature"> |
|
|
<h3>🌟 Complex Motion Generation</h3> |
|
|
<p>Trained on +65.6% more images and +83.2% more videos, achieving superior performance in motions, semantics, and aesthetics</p> |
|
|
</div> |
|
|
</div> |
|
|
|
|
|
<div class="models-section"> |
|
|
<h3 class="models-title">Model Downloads</h3> |
|
|
<div class="models-grid"> |
|
|
<div class="model-category"> |
|
|
<h4>Text to Video Models</h4> |
|
|
<div class="model-links"> |
|
|
<a href="https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B" target="_blank" rel="noopener noreferrer" class="model-link"> |
|
|
<span class="model-name">T2V-A14B</span> |
|
|
<span class="model-tag">Base</span> |
|
|
</a> |
|
|
<a href="https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers" target="_blank" rel="noopener noreferrer" class="model-link"> |
|
|
<span class="model-name">T2V-A14B</span> |
|
|
<span class="model-tag">Diffusers</span> |
|
|
</a> |
|
|
</div> |
|
|
</div> |
|
|
<div class="model-category"> |
|
|
<h4>Image to Video Models</h4> |
|
|
<div class="model-links"> |
|
|
<a href="https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B" target="_blank" rel="noopener noreferrer" class="model-link"> |
|
|
<span class="model-name">I2V-A14B</span> |
|
|
<span class="model-tag">Base</span> |
|
|
</a> |
|
|
<a href="https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers" target="_blank" rel="noopener noreferrer" class="model-link"> |
|
|
<span class="model-name">I2V-A14B</span> |
|
|
<span class="model-tag">Diffusers</span> |
|
|
</a> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
|
|
|
<div class="model-highlight"> |
|
|
<h4>Efficient High-Definition Hybrid TI2V</h4> |
|
|
<p>5B model with advanced Wan2.2-VAE achieving 16×16×4 compression ratio. Supports both text-to-video and image-to-video generation at 720P resolution with 24fps.</p> |
|
|
<div class="highlight-links"> |
|
|
<a href="https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B" target="_blank" rel="noopener noreferrer" class="highlight-link"> |
|
|
<span>TI2V-5B Base</span> |
|
|
</a> |
|
|
<a href="https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers" target="_blank" rel="noopener noreferrer" class="highlight-link"> |
|
|
<span>TI2V-5B Diffusers</span> |
|
|
</a> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
|
|
|
<div class="redirect-section"> |
|
|
<p class="redirect-text">Redirecting to WaveSpeedAI...</p> |
|
|
<div class="progress-bar"> |
|
|
<div class="progress"></div> |
|
|
</div> |
|
|
<a href="https://wavespeed.ai/collections/wan-2-2" class="cta-button" target="_blank" rel="noopener noreferrer">Visit Now →</a> |
|
|
<p class="huggingface-link"> |
|
|
Also available on <a href="https://huggingface.co/Wan-AI" target="_blank" rel="noopener noreferrer">Hugging Face</a> |
|
|
</p> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</body> |
|
|
</html> |
|
|
|
