Wan 2.2 Video AI Model – Introduction
Developed by Alibaba’s Tongyi Lab, the newly open-sourced Wan 2.2 series sets the benchmark in text-to-video, image-to-video, video editing, text-to-image, and video-to-audio creation.
* Peak Performance: T2V-14B and I2V-14B achieve new SOTA results; the lightweight T2V-1.3B runs on just 8 GB VRAM, producing a 5-second 480 P clip on an RTX 4090 in under 4 minutes.
* Multilingual Text: the world’s first video model to generate dynamic on-screen text in both Chinese and English.
* Cinematic Quality: physics-accurate motion, intricate choreography, and fluid camera work for true movie-grade visuals.
* Effortless Creation: intuitive, zero-learning-curve interface with start/end-frame control, plus custom resolution and frame-rate settings.
Experience Wan 2.2 today—and transform your ideas into motion.