Wan 3.0
Up to 30s clips with native audio and multimodal references.
What it can do
- Made by
- Alibaba
- Best for
- Long takes with sound
- Inputs
- Text to video · Image to video (first frame) · First and last frame · Reference images (up to 10) · Video reference · Driving audio
- Aspect ratios
- adaptive, 16:9, 4:3, 1:1, 3:4, 9:16
- Resolutions
- 480p, 720p, 1080p
- Duration
- 2–30s
- Native audio
- Yes