Skip to main content

Uncensored — This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer.Browse every model at this filtering level
vidu/q3-pro/image-to-video

Vidu Q3 Pro image-to-video animates an opening frame and a movement prompt into 1 to 16 whole seconds of 540p video. Audio is generated in the same pass and is on by default, and the output follows the frame's shape.

From $0.054/s
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
    palace-belly-dance-lanterns

    `image_url` is the opening frame: a belly dancer in a jewelled turquoise top, a gold coin hip belt and a layered turquoise chiffon skirt stands with her arms raised in a palace hall hung with brass lanterns, silk curtains between the arches and a ring of seated musicians. From that pose she dances: her hips sway, her arms wave above her head, she spins so the skirt flares out wide while a red curtain billows behind her and the camera circles around her, and she finishes facing the camera with a slow smile. `resolution` is `540p`, the tier this endpoint offers, and `generate_audio` is `true`, so the clip has sound.

    • 540p
    • audio
    • 5s
  • Output6s
    dwarf-forge-sparks

    Uplight from below plus repeated impact: sparks have to burst on the strike and not between them, and the audio generated in the same pass has to land on the same frames. That is the useful thing to test on an endpoint that renders sound alongside the picture rather than after it. `resolution` is fixed at `540p` here, so the variable worth spending on is `duration_seconds`, which runs from one to sixteen.

    • 540p
    • 6s
  • Output8s
    stage-frame

    Eight seconds from one drawn stage frame. The prompt carries the wink, the dolly-in and the crowd roar; the costume and the line work come from the image.

    • 540p
    • audio
    • 8s
  • Output5s
    vertical-deliverable

    The still was exported vertical, so the clip comes back vertical. The prompt only has to carry the walk and the camera retreating ahead of her.

    • 540p
    • audio
    • 5s

This example starts at $0.054 per output second. The Playground updates the estimate when you change the settings.