Wan 3.0 Video Edit
Wan 3.0 Video Edit rewrites an existing clip from a plain-language instruction — remove an object, change an outfit or a character's age, restyle or relight the whole shot, or even change what someone says. It is the editing mode of Alibaba's unified Wan 3.0 model, keeps the original framing and length, and can pull new looks from up to ten reference images.
Input
Describe the edit: what to remove, replace, restyle or relight, or the new line a character should say.
The clip to edit. Clips longer than 15 seconds are trimmed to their first 15 seconds.
Optional images (up to 10) showing a new outfit, product, character or style to bring into the clip.
0 / 10
Optional audio clips (up to 5, 15 s in total) for voice or sound reference.
0 / 5
Output resolution. Higher resolutions cost more per second.
Generate new audio for the edited clip. Turn off to keep the original soundtrack.
Let the model rewrite and enrich a short prompt before editing.
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-video-edit \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'