Three input modes
Text, first and last frames, or multimodal references.
New · Alibaba
Build shots from text, frames or multimodal references with native audio and clear per-second pricing.
Create a Wan 3.0 Prime video
Creator
Video generator
No additional settings
Choose text, frames or references in a single workspace.
Text, first and last frames, or multimodal references.
Match draft speed or final-delivery resolution.
Generate audio and tune prompt expansion and thinking.
Workflow
Select the exact mode and provide only matching assets.
Set resolution, duration, aspect ratio and audio.
Review the estimated credits before generating.

A Wan 3.0 Prime example showing visual detail and composition.
Answers about input modes and cost.

Direct your shot with clear controls and an upfront per-second estimate.