Wan 2.5 image-to-video from Alibaba animates one opening frame into a 5 or 10 second clip with generated sound, at 480p, 720p or 1080p. A prompt carries the motion, and an optional audio track can drive the timing.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
two-under-one-umbrella Rain on an umbrella is a sound cue with a visible source, which makes it the right subject for an endpoint that renders audio with the picture. `image_url` sets the frame and the prompt keeps the two figures nearly still: the motion in this clip belongs to the water. `duration_seconds` is 5 or 10 and nothing else, and when the whole event is continuous the shorter one is usually enough.
- 720p
- 5s
- Output5s
serum-bottle-turn The frame fixes the label and silhouette; the prompt asks only for a camera arc and moving light.
- 720p
- 5s
- Output10s
slip-dress-turn A ten-second 1080p take from a studio portrait, with the negative prompt stopping jewellery and extra people from appearing.
- 1080p
- 10s
This example starts at $0.045 per output second. The Playground updates the estimate when you change the settings.