Today for AI
HOT RADAR
llmHEAT 6.6°

AI CLUSTERED EVENT · 10/8/2026

Vidu Q4 Preview Launches with Low Cost and Multi-Reference Control, Testing Video Model Efficiency Parity

1 reports archived1 independent sourcesupdated 10/8/2026, 20:19:00
Synthesis & Latest Updates
1 Sources Cross-Validated

Shengshu Technology released Vidu Q4 Preview, featuring a launch price of 0.09 RMB per second and support for up to 15 reference images, aiming to democratize video generation through extreme cost-efficiency. The update focuses on enhanced character performance, cinematic language, and complex visual effects, supporting 2K/4K output while balancing performance, efficiency, and usability. Although currently in preview stage with some technical details undisclosed, its pricing strategy and reference control capabilities signal an industry trend towards a 'DeepSeek moment' for video models.

LATEST/Shengshu Technology released Vidu Q4 Preview, featuring a launch price of 0.09 RMB per second and support for up to 15 reference images, aiming to democratize video generation through extreme cost-efficiency. The update focuses on enhanced character performance, cinematic language, and complex visual effects, supporting 2K/4K output while balancing performance, efficiency, and usability. Although currently in preview stage with some technical details undisclosed, its pricing strategy and reference control capabilities signal an industry trend towards a 'DeepSeek moment' for video models.

HEAT TRENDHourly heat curve

21 fully observed hours
Now
6.8
Peak
11.821:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. 机器之心 (微信公众号)T2·68 pts

    Vidu Q4 Preview Launches with Low Cost and Multi-Reference Control, Testing Video Model Efficiency Parity

    Original: 视频DeepSeek时刻？Vidu Q4 Preview背后的效率账与世界模型底气

    • Vidu Q4 Preview offers a launch price as low as 0.09 RMB per second, significantly lowering the barrier to entry.
    • Supports up to 15 reference images and voice inputs, enhancing multi-subject consistency and controllability.
    • Focuses on improving character performance subtlety, camera movement tension, and complex special effects.