New video model: WAN 3.0 is now available with native audio, enhanced reasoning, and clips from 2 to 30 seconds at 480p, 720p, or 1080p.
- Parallel generations: all video generation apps can now create multiple videos at once, running in parallel.
- WAN 3.0: prompt-driven generation or first/last-frame animation. [Text-to-Video] [Image-to-Video]

Generate a video from a text description

Processing time: ~1-15 min

powered by Alibaba AI

Prompt

Describe the scene, motion, and audio to generate.

Resolution

The resolution of the video

480p

Aspect ratio

The aspect ratio of the video

Adaptive

Duration

The duration of the video in seconds

Generate audio

Generate synchronized audio together with the video.

Yes

Available in Power Mode

Count

Number of results to generate in parallel.

More options

Enable prompt expansion

Expand the prompt before generating the video.

Yes

Enable thinking

Enable enhanced reasoning before generating the video.

Seed

Unique output seed number. If not provided, the output will be random.