ShengShu launches Vidu Q4 Preview: 16-second audio-video clips from $0.014/sec
lmoroney · x · 2026-10-08
ShengShu Technology released a public preview of Vidu Q4 Preview, its next flagship audio-video model, available in Vidu's web app and via API as viduq4-preview.
Key points:
- Reference control: up to 15 reference images for characters, wardrobe, props, and locations, plus up to 3 audio clips to keep a character's voice consistent.
- Specs: clips up to 16 seconds with sound generated alongside the picture, output from 540p to 4K with 10-bit color.
- Pricing: launch release quoted from $0.014/sec; a later release lists $0.045/sec at 540p and up to $0.39 at 4K — check current rates before budgeting.
- Practical tip: iterate at 540p/720p until camera moves and performance work, then upscale for final shots.
Related event: Vidu Launches Q4 Preview Video Model, Debuts Third on Leaderboard(3 posts)→
More from Multimodal
- AI-generated feature 'A Woman Asleep' enters major film festival's main competition — lmoroney · 2026-10-08
- vLLM-Omni technical report: a unified serving runtime for omni-modal generation — vllm_project · 2026-10-08
- Alaskan Raven Couple 'Conversing' Video Goes Viral on X — ZeroStateReflex · 2026-10-08
- Claude turns OpenAI's 198-page Erdős conjecture proof into a 2-minute narrated 3D animation — imjustnewatai · 2026-10-08
- AI Short Film About Relationships Made With ComfyUI Agent Driver and Multi-Model Pipeline — TheHollywoodGeek · 2026-10-08
- SGF+ decouples denoising and context-writing gradients, enabling 24-hour video from 5s training — Zihan Su · 2026-10-08