Bring a still to life
vidmoat-image-live-1: animate a still. See the model card under Models. Camera moves use depth parallax; ambient, object, face, body and vehicle motion use the generative tier, our own Wan 2.2 model, where it is available. Nothing is added to the picture. Returns a job to poll.
Priced per second: 8 credits a second for camera moves and region cinemagraphs, 2 to 10 seconds (40 for the 5-second default); 24 credits a second for the generative tier, 4 or 5 seconds in 16:9, 9:16 or 1:1, without loop, taking about 2 to 5 minutes. quoteOnly shows which tier a request gets, and the quote is the charge. Setting region, motion, box, strength or direction keeps a request on the cheaper tiers. Anything appearing, pouring, breaking or transforming is refused before charging with a 400 that points to Generate a video, and so are faces, people, vehicles and turning objects where the generative tier is not available. Every clip is measured before delivery; one that does not move, moves outside its region or drifts from the still ends FAILED and is refunded. Video only, no audio track. Uses the ai.video scope so the same key can poll the job.
Request
- Base URL: https://api.vidmoat.com/v1
- URL: https://api.vidmoat.com/v1/ai/live-images
- Auth: HTTP bearer
Request body
Response
Bring a still to life
Changes
No recorded changes to this operation across all 1 revision of this API.