Alibaba's Wan 2.2 image-to-video animates one opening frame into a silent five-second clip at 480p or 720p. The frame fixes subject, wardrobe, set and light, while a required prompt carries the motion.
Filtering differs by endpoint: Image to video — Softened, Text to video — Filtered.
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.
- Output6s
window-dusk-turn A still of a woman at a window at dusk, animated into a turn and two slow steps toward the camera. The prompt only describes what happens after the first frame (letting go of the curtain, the walk, the half smile) and leaves the look to the image.
- 720p
- Output6s
serum-bottle-arc The frame fixes the label and silhouette; the prompt asks for one thing, a slow quarter-turn arc while a band of window light travels across the glass. That light starts at the neck, crosses the label and slides off the base — the bottle never moves. `resolution` `480p` is all this simple shot needs; swap in a different `image_url` and the structure carries over.
- 480p
- Output6s
slip-dress-step The portrait already fixes the dress, the light and the grey backdrop, so the prompt only choreographs three beats: the weight shift, two steps toward the lens, and a hair tuck that lands on a held look. `resolution` `720p` keeps the satin sharp enough to read the light catching it. The same structure works for any studio portrait.
- 720p
This example starts at $0.24 per request. The Playground updates the estimate when you change the settings.