wan 3.0 ai video generator

wan 3.0 ai video generator is a third-party browser interface for Wan 3.0, the video generation model from Alibaba’s Tongyi Lab (released August 2026). It runs in your browser and does not require an Alibaba Cloud account, region/key setup or a local GPU.

You can feed the model one of four input types: a text prompt up to 20,000 characters; a single photo used as the first frame, the last frame, or both; a reference set (up to 10 images, 5 video clips and 5 audio tracks) that you address by number inside the prompt so a face, product or voice can remain consistent; or a document (PPT, PDF, spreadsheet or public web page) up to 50 pages, which the model reads and turns into footage rather than just narrating slides. It also supports rewriting existing footage without fully regenerating it.

Outputs are produced in one pass as a whole clip between 2 and 30 seconds at 30 fps, and can be rendered at 480P, 720P or 1080P. Speech, effects and music are generated along with the picture, and turning sound off does not change the cost because processing is a single pass.

• Free clip uses the wan3.0-video model ID, the same engine used by paid plans.
• Every result shows the model, resolution, length and upstream task ID; failed or expired jobs are refunded to credits automatically.
• Pricing is freemium with paid plans at $9.90, $29.90 and $79.90 per month when billed yearly; credits are consumed at the same per-second rate across plans.

Official site: https://wan-3.run/