WAN 3.0 is an AI video generation platform for text-to-video, image-to-video, and reference-to-video workflows. A single clip can run up to 30 seconds and render up to 1080p.
What you can create
- Text to video - describe a scene and let WAN 3.0 build the shot.
- Image to video - animate a still image while keeping its composition.
- Reference to video - keep a subject or a style consistent across shots.
- Longer sequences - carry one idea through several connected shots.
How credits work
Every paid plan includes a credit allowance for generation. Image requests cost fewer credits than video requests, and longer or higher resolution video costs more. You can see the current allowance for each plan on the pricing page.
Getting started
- Sign in with Google.
- Open the video generator and describe the shot you want.
- Pick a model and a resolution, then generate.
- Review the result in your workspace history.
