Vidu Q4 combines images and voice references for multi-shot stories with expressive performances and native audio. Direct the action, camera moves and effects in clips up to 16 seconds long, with output up to 4K.
Give characters, outfits, products and locations a clear visual starting point. Add different views of a character rather than relying on one image.
Guide up to three voices with audio references, matching speech and expression to the performance.
Build a sequence of wide shots and close-ups in one generation. Guide camera movement and cuts with your prompt while keeping characters and settings recognizable.
Bring smoke, explosions and particles into the shot, with lighting and visual detail at 2K or 4K.
| Control | Image-to-video | Reference-to-video |
|---|---|---|
| Visual input | One first-frame image | 1–15 reference images |
| Clip length | 3–16 seconds | 3–16 seconds |
| Output resolution | 540p, 720p, 1080p, 2K or 4K | 540p, 720p, 1080p, 2K or 4K |
| Audio | Dialogue and sound effects | Dialogue and sound effects; up to 3 voice references |
| Capability | Vidu Q4 Preview | Vidu Q3 on YouArt |
|---|---|---|
| Starting point | A first-frame image or multiple image references | Text, or one first-frame image |
| Maximum resolution | Up to 4K | 1080p |
| Voice references | Up to 3 | No voice-reference input |
| Audio generation | Native dialogue and sound effects | Optional generated audio |
While you wait, create with Vidu Q3 on YouArt. Start with a prompt or an image, then refine the motion, framing and sound.
Vidu is a trademark of ShengShu Technology. YouArt is an independent platform, not affiliated with or endorsed by ShengShu Technology.
