Key Features

Mixture-of-Experts (MoE) architecture
Cinematic-level aesthetics
Complex motion generation
Efficient high-definition hybrid TI2V
Support for text-to-video and image-to-video generation
720P resolution with 24fps
Compatibility with consumer-grade graphics cards
Fast inference speed

Wan2.2 is trained on a significantly larger dataset than its predecessor, Wan2.1, with +65.6% more images and +83.2% more videos. This expansion enhances the model's generalization across multiple dimensions such as motions, semantics, and aesthetics, achieving top performance among all open-sourced and closed-sourced models. The model also supports both text-to-video and image-to-video generation at 720P resolution with 24fps and can run on consumer-grade graphics cards like 4090.


Wan2.2 open-sources a 5B model built with the advanced Wan2.2-VAE that achieves a compression ratio of 16×16×4. This model supports both text-to-video and image-to-video generation at 720P resolution with 24fps and can also run on consumer-grade graphics cards like 4090. It is one of the fastest 720P@24fps models currently available, capable of serving both the industrial and academic sectors simultaneously. The model is also compatible with various frameworks and tools, including PyTorch, Hugging Face, and ModelScope.

Get more likes & reach the top of search results by adding this button on your site!

Embed button preview - Light theme
Embed button preview - Dark theme
TurboType Banner

Subscribe to the AI Search Newsletter

Get top updates in AI to your inbox every weekend. It's free!