Vidu Q3 image-to-video takes an opening frame and a prompt, both required, and animates what happens next for 1 to 16 whole seconds. Choose 540p, 720p or 1080p; audio is generated with the picture unless you switch it off.
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
high-key-morning-fall The opposite exposure to the clip beside it: blown-out morning light through a sheer curtain, dust visible in the beam, and a slow handheld drift instead of an arc. Three linked actions run in five seconds — the stretch, the fall back across the bed, the turn to camera — and none of them is described in the frame.
- 720p
- audio
- 5s
- Output5s
clifftop-gust Wind as the subject: the long grass runs in waves, the dress and hair stream sideways and snap, and a steadicam arcs around her while she leans into the gust. Everything is one continuous force acting on three different materials, which is a harder test of an animated still than a person simply turning round.
- 720p
- 5s
- Output5s
rain-window-strap Mixed light on skin and satin: pink and teal neon through a rain-streaked window, a slow push-in, and a turn from the glass toward the camera while one hand settles at her shoulder. The small gesture has to stay where the still put it, and the neon has to keep crawling across the wet glass behind her.
- 720p
- audio
- 5s
- Output5s
rooftop-open-shirt-dusk One man alone on a rooftop at dusk: a warm gust lifts the open linen shirt, he turns from the skyline and runs a hand through his hair while the camera orbits. The backlight has to flare past his shoulder as the angle changes, and the fabric has to move with the wind rather than with the camera.
- 720p
- audio
- 5s
- Output5s
balcony-two-women-dawn Two people in one frame on a Paris balcony at dawn, with a locked-off camera: one lifts her head from the other's shoulder, the other tucks her hair behind her ear and they lean their foreheads together. Keeping both faces, both outfits and the coffee cup consistent through the contact is the test; the prompt says both stay in frame because an earlier take let one of them walk out of it.
- 720p
- audio
- 5s
This example starts at $0.07 per output second. The Playground updates the estimate when you change the settings.