Alibaba's Wan 2.6 image-to-video animates one opening frame into exactly 5, 10 or 15 seconds with generated sound, at 720p or 1080p. Choose a single take or a multi-shot edit, and add an audio track to drive timing.
Filtering differs by endpoint: Image to video — Uncensored, Text to video — Uncensored, Reference 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.
- Output5s
counter-slide-approach - 720p
- 5s
- Output10s
kitchen-three-shots Three shots cut out of a single opening frame: the same kitchen covered close, medium, then close again. `image_url` fixes the set once and `shot_type` decides whether the call returns one continuous take or that sequence, so coverage costs one request instead of three. Each numbered line carries its own shot size, and the sound for all three is rendered in the same pass against the picture.
- 1080p
- 10s
- Output15s
evening-apartment-story `shot_type` set to multi and `enable_prompt_expansion` true turn one static room into three distinct cuts: the wide shot as the lamp flickers and city lights click on, a close-up where the blanket has slid off the armchair, and the door swinging open with hallway light spilling in. `duration_seconds` is 15.
- multi
- 720p
- 15s
- Output5s
serum-bottle-drop The prompt narrows to one instant: the dropper lifts, a drop falls, and slow rings spread while the light band on the glass brightens. `resolution` is 1080p with `seed` pinned at 20251216, holding the same macro framing. Watch the ripple reach even the tabletop reflection, not just the liquid surface.
- 20251216
- 1080p
- 5s
This example starts at $0.09 per output second. The Playground updates the estimate when you change the settings.