Vidu Q4 Preview

Everything that is known about Vidu Q4 Preview, the first public release of ShengShu Technology’s next flagship video model: when it launched, what it can do, what it can’t yet, and what it costs.

Updated 2026-10-09

Developer
Vidu, by ShengShu Technology
Released
October 7, 2026, as a public preview of Vidu Q4
Modes
Image to Video, Reference to Video
References
Up to 15 images and 3 voice clips (3–12 s each)
Length
3 to 16 seconds
Resolution
540p, 720p, 1080p, 2K, 4K (10-bit color)
Aspect ratio
Follows the image, or 16:9, 9:16, 1:1, 4:3, 3:4 for references
Sound
Dialogue and sound effects generated with the video
Text to video
Not available in the Preview
Official launch video from Vidu, embedded from YouTube. Shown for reference; this site is independent of Vidu.

What is new in Vidu Q4 Preview

Vidu Q4 is built around performances. Facial expression, emotion, body movement and voice are generated together, so a character can deliver a line with the matching expression instead of a mouth moving over a neutral face.

The model also handles the camera: it can cut between angles within one clip and keep characters consistent from shot to shot. ShengShu highlights fast scenes (chases, fights and stunts) and effects such as explosions, fireworks and particles as the areas that improved most.

Output goes up to 2K and 4K with 10-bit color, and the reference system grew to 15 images and 3 voice clips in a single request.

Preview vs the full Vidu Q4

Vidu released the Preview ahead of the full Q4 model so creators can use it on real projects and shape the final version. No date has been announced for the full release, and ShengShu says final pricing and supported resolutions may still change.

Practically, the Preview is a production-ready model with two modes. Expect the full Q4 to add or change features; this page will be updated when it ships.

Vidu Q4 Preview vs Vidu Q3

Vidu Q3 offered text-to-video, image-to-video and start-and-end-frame video with sound, up to 16 seconds. Vidu Q4 Preview keeps the 16-second ceiling and the sound, but drops text-to-video for now, raises resolution to 4K, and takes far more reference material.

If you start from an idea rather than an image, create or pick a reference image first; everything after that (motion, dialogue, camera) is steered by the prompt.

Vidu Q4 Preview pricing

On Vidu’s API the list price is per second of video and rises with resolution: about $0.045 per second at 540p up to $0.39 per second at 4K, with launch discounts on credit packages. Vidu’s own apps sell subscriptions with their own credit rates.

Here you pay per second with one-time credit packs: from 10 credits per second at 540p to 80 at 4K, with the exact cost shown before each video and failed videos refunded.

Where to use Vidu Q4 Preview

Vidu Q4 Preview is available on Vidu’s own web app, through the Vidu API, inside partner apps such as Perfect Corp’s YouCam, and on independent sites like this one, which run the model through the official API.

Vidu Q4 Preview FAQ

  • On October 7, 2026. ShengShu Technology announced it as the first public preview of Vidu Q4, ahead of the full model.

  • No. It runs on paid credits on Vidu’s platform and on third-party sites. Here the cheapest way to try it is a one-time trial pack; nothing renews.

  • No. The Preview supports Image to Video and Reference to Video only. Start from at least one image.

  • From 3 to 16 seconds per generation, at 540p, 720p, 1080p, 2K or 4K.

  • No date has been announced. The Preview is available now; we will update this page when the full model launches.