Vidu Q4 Preview image-to-video animates an opening frame into a 3 to 16 second clip at 540p up to 4k, keeping the shape of your frame. Sound and quoted dialogue are generated with the picture. In our tests NSFW content came through; since 9 October, the Very strong level is refused.
Filtering differs by endpoint: Image to video — Uncensored, Video extension — Uncensored, Reference to video — Light.
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
dressing-room-zip A 16:9 frame at 720p. The line is in quotes in the prompt and was spoken in the output. Describe the beats in order (turn, reach, zip, line) so each lands inside the five seconds.
- 41001
- 720p
- 5s
- Output5s
hammam-steam-walk A 9:16 frame gives a 720 x 1280 clip. One walk toward the camera is enough for five seconds; steam and dripping water came through in the sound.
- 41002
- 720p
- 5s
- Output5s
silk-morning-kiss A frame of two women in morning light, and a prompt that asks only for a slow kiss and a smile. With two people in frame, keep to one slow action so both faces stay steady.
- 41003
- 720p
- 5s
This example starts at $0.045 per output second. The Playground updates the estimate when you change the settings.