The Q4 Preview introduces significant technical upgrades, including support for up to 15 image references and three audio clips to maintain consistency across scenes. By allowing users to anchor characters, wardrobe, and environments through these references, the model seeks to solve the persistent challenge of maintaining visual continuity in AI-generated narrative content. Shengshu Technology emphasizes that the move toward lower costs is intended to encourage experimentation, allowing creators to refine expressions and test multiple camera angles without the financial burden associated with previous iterations.
Vidu Unveils Q4 AI Video Model With Aggressive Pricing
Priced at just $0.014 per second, the new Vidu Q4 Preview aims to democratize high-end AI video production. Shengshu Technology’s latest flagship model focuses on granular creative control, offering independent filmmakers and studios a cheaper way to iterate on complex character performances, cinematic camera work, and high-fidelity visual effects.
Beyond character performance, the update targets technical polish in high-action sequences. The model features enhanced coordination between camera movements and VFX, such as explosions and particle effects, while offering output resolutions up to 4K with 10-bit color depth. By releasing this preview ahead of the final Q4 model, the company is soliciting feedback from real-world production workflows to calibrate the tool for its full release. The platform is currently accessible via Vidu’s web portal and API, with promotional pricing designed to provide up to five times more output than comparable market alternatives.
Comments (0)
No comments yet. Be the first!