Wan 3.0 is an all-in-one video generation and editing model developed by Alibaba’s Tongyi Lab and is currently available in public beta. It is designed for advertising, e-commerce, filmmaking, character animation, video editing, and document-to-video creation. Its advantages include native video generation of up to 30 seconds, production-grade character consistency, lifelike visuals and sound, and unified support for reference, editing, replication, and motion driving. It can use text, images, audio, video, documents, spreadsheets, presentations, and webpages as creative references. Compared with Wan 2.7, which separated text-to-video, image-to-video, reference generation, and editing into different models, Wan 3.0 combines them into one more flexible workflow.