Wan 2.2

Developers, indie creators and small studios who want to turn a prompt or a still image into a short clip will find Wan 2.2 a practical place to start.

Wan 2.2 is an open source AI video generator that handles both text-to-video and image-to-video, and its Apache 2.0 license means you can inspect and build on it.

Commercial use of the generated videos is allowed.

Under the hood it uses a Mixture-of-Experts architecture and a 64x VAE compression scheme meant to keep quality up while cutting cost.

Most videos take 30 to 60 seconds to generate, and a 5-second 720P clip finishes in under 9 minutes.

Wan 2.2 also adds sound effects and lip sync to its output.

The Starter plan is limited to 360p and clips of 5 to 30 seconds, and higher resolutions and longer videos up to 60 seconds depend on Pro and Enterprise plans, which are marked as coming soon.

Pricing is enterprise-oriented.

Data is processed in real time and not stored.