vidu/q4-preview/reference-to-videoVidu Q4 Preview reference-to-video builds one scene from 1 to 15 reference images and up to 3 voice clips, in 16:9, 9:16, 1:1, 3:4 or 4:3. Clips run 3 to 16 seconds at 540p to 4k with generated sound. It is lightly filtered: from the Moderate level up it tones down or refuses most NSFW requests.
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
emerald-robe-fitting Three references in order: a portrait, a robe photo and an empty fitting room. The prompt names them by position, and her face, the robe and the room's gilded mirror and velvet curtains all carried over.
- 41004
- 720p
- 16:9
- Output9s
whisper-lock-the-door One portrait and one voice clip, 9:16 at nine seconds. The whispered line is written in quotes in the prompt; the clip sets the voice. Without the line in the prompt a run produced no speech.
- 41015
- 720p
- 9:16
- Output5s
elevator-loosened-tie Two portraits, each referred to by position, and one slow action in a 9:16 elevator. Both faces were kept. A reference scene with two people works best with a single beat.
- 41006
- 720p
- 9:16
This example starts at $0.045 per output second. The Playground updates the estimate when you change the settings.