Skip to main content

Softened — This model returns a result instead of an error, but requests beyond its own limits come back toned down. The call still succeeds and is still billed, so check the output rather than the status code. Image to video — Softened; Text to video — Filtered.Browse every model at this filtering level
alibaba/wan-2.2/text-to-video

Alibaba's Wan 2.2 text-to-video turns a written shot into one silent five-second clip. Choose 16:9 or 9:16 and 480p or 720p, with optional prompt expansion and a seed to repeat a draw.

Filtering differs by endpoint: Image to video — Softened, Text to video — Filtered.

From $0.24/request
Run model

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
    snow-platform-one-coat

    Written from nothing at `resolution` `720p` in `16:9`. This endpoint returns five silent seconds — there is no audio pass and no duration to choose — so the brief is built entirely out of things the eye can carry: falling snow, breath clouding, a lamp that flickers. When no sound is coming back, put a visible rhythm in the frame instead of relying on ambience to fill the clip.

    • 720p
    • 16:9
  • Output5s
    lighthouse-stairs

    One action and one camera position in 16:9 at 480p: the cheapest way to check whether a shot idea works in motion.

    • 480p
    • 16:9
  • Output5s
    night-market-vertical

    A 9:16 take at 720p with a fixed seed, so the same framing can be compared across prompt edits.

    • 250728
    • 720p
    • 9:16

This example starts at $0.24 per request. The Playground updates the estimate when you change the settings.