Shengshu releases Vidu Q4 Preview on October 8 with 15 reference images and 4K output at CNY 0.09 per second

Beijing-based Shengshu released Vidu Q4 Preview, the first preview of its next flagship video generation model, on October 8. The model accepts up to 15 reference images and 3 reference audio clips, improves character performance consistency, camera movement, and complex visual effects, and outputs up to 540p to 4K video in 10-bit color. A single generation runs 3 to 16 seconds, and only image-to-video and reference-to-video modes are available at preview. The API identifier is viduq4-preview, priced from $0.045 per second at 540p up to $0.39 per second at 4K, with a 30% discount on image-to-video and reference-to-video through November 30. Shengshu's SaaS product lists a launch promotional price starting at CNY 0.09 per second. The model generates aligned sound with picture, including dialogue and effects, and reference audio keeps character voices consistent across shots. Shengshu was founded in 2022 by Tsinghua University researchers, with Vidu first unveiled in April 2024. The preview ships ahead of the final Q4 model so creators can run real projects and shape the release version.