Wan 3.0 Prime Reference to Video
Wan 3.0 Prime Reference to Video is the premium tier of Alibaba's Wan 3.0 reference mode, aimed at final deliverables rather than drafts. It builds a video of up to 30 seconds, with sound, from your own images, clips and audio — and is the tier to reach for when a character, a product label or a brand mascot has to stay locked across a reference-heavy shot.
Input
Describe the shot. Refer to references as Image 1, Video 1, Audio 1 and so on, numbered per type in upload order.
Up to 10 reference images for characters, products, style or setting. Add at least one image, video or audio reference.
0 / 10
Up to 5 MP4 or MOV clips (1-15 s each, 15 s in total) for motion, camera or subject reference. Their length is billed too.
0 / 5
Up to 5 audio clips (15 s in total) for voice, music or rhythm reference.
0 / 5
Output aspect ratio.
Output resolution. Higher resolutions cost more per second.
Video length in seconds (2-30). With reference videos, their length plus this duration must stay within 30 s.
Generate a synchronised soundtrack with the video. Does not change the price.
Let the model rewrite and enrich a short prompt before generating.
Seed for reproducible results. Leave empty for a random seed.
Output
Run the model to see output here.
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/alibaba/wan-3.0-prime-reference-to-video \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'