Omni-Creation
Up to 20 reference assets, with document and webpage parsing.
Up to 20 reference assets, with document and webpage parsing.
More complete storytelling and creative freedom.
Improve delivery certainty for production workflows.
Elevated realism, texture, and sound design.
More controllable editing to boost creative efficiency.
Create without barriers—bring your ideas to life on Wan with text, images, and videos.
Build without limits—power your business with our API for seamless, high-quality visual generation.
Explore API
Innovate without boundaries — harness open-source models for advanced performance and exceptional quality.
View on GitHubCast referenced characters into new scenes, supporting multi-person and human-object interactions with consistent appearance and voice.
Generate videos up to 30 seconds with auto scene splitting for more stable native audio-visual videos.
Cinematic precision with sophisticated motion and highly reliable prompt execution.
Multi-dimensional instruction-based video editing for re-creating visuals, storylines, and environments.

Photorealistic results with expressive styles and consistent prompt alignment.

Enables easy conversational edits, references, and image creation.

Unified Model for Character Animation and Replacement.
Learn More
An Audio-Driven Cinematic Video Generation Model.
Learn More
Wan2.2 scales with MoE, delivering stronger models and more beautiful videos, pushing open-source video generation to new frontiers.
Learn MoreUnleash your creativity anytime, anywhere with our official app.
App not available in your region? Try our mobile web version.