Wan 2.6 Flash reference-to-video from Alibaba casts people, animals or objects from up to five stills and clips into a new scene described by your prompt, on the faster, lower-cost Flash tier. Clips run 2 to 10 seconds at 720p or 1080p, silent by default or with a generated soundtrack.
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
rooftop-slow-dance Two stills and nothing else: a portrait of each person in `reference_image_urls`, named character1 and character2 in the prompt, cast into a scene neither was photographed in. `generate_audio` is on, so the wind, the traffic and the laugh written into the prompt come back as sound, at twice the per-second rate. Stills are not billed, so the 5 seconds of output are the whole bill.
- 720p
- 16:9
- audio
- Output5s
quay-clip-and-still A clip and a still in one request. The five-second harbour clip in `reference_video_urls` becomes character1 and the portrait in `reference_image_urls` becomes character2, because clips are numbered before stills. The clip's seconds are billed with the output; sound is off here, so the picture is ready for your own mix.
- 720p
- 16:9
- 5s
This example starts at $0.022 per output second. The Playground updates the estimate when you change the settings.