LiveWan 3.0 is live: 30-second clips, 1080p, native sound and dialogue. Try it now →

Now running Wan 3.0, Alibaba's latest AI video model

Wan AI Video Generator.
Render anything.

Turn text or images into finished videos with sound, dialogue and camera direction, powered by Alibaba's new Wan 3.0 model.

Drop files, then mention them in your prompt with @
  • image1@[image1]
  • image2@[image2]
  • @[video1]
Ratio
Features

What the Wan AI video generator does.

How it works

How to use Wan in three steps.

  1. 01

    Write your prompt

    Describe the scene, the camera move and the line your character says. Plain language works, Wan understands the language of film.

  2. 02

    Add an image or references (optional)

    Drop a photo as the first frame for image-to-video, or on Wan 2.7 attach reference images and clips and tag them in the prompt.

  3. 03

    Generate and export

    Get up to 30 seconds at up to 1080p in 16:9, 9:16, 1:1 and more, sized for TikTok, Reels, YouTube Shorts and ads.

Showcase

Videos made with Wan.

Make your own →
Use cases

What people make with Wan.

Benchmarks

Wan is a top-ranked AI video model family.

Now live

Wan 3.0 is here.

30-second scenes
Whole stories, one generation
Adaptive framing
The model picks the best composition
Native dialogue
Quoted lines, lip-synced on screen
Start creating today3.0 is the default model for every account, on every plan, at no extra cost.
Pricing

Wan pricing: start free.

Every plan includes AI videos & images, a commercial licence and a media gallery. The only difference is how much you make.

Don't want to commit? No problem.

Grab a one-time credit pack, no subscription, and the credits never expire.

Just browsing? The free plan gets you a taste, a couple of videos a month, card not required.

FAQ

Wan FAQ.