Everything About AI
AsianFin -- Zhu Jun, Vice Director of the Tsinghua University AI Research Institute and Founder and Chief Scientist of Shengshu Technology, announced the release of the latest multimodal video generation model, Vidu Q1, which will be globally launched in April.
The Vidu Q1 model stands out from its predecessors with its focus on controllability. It allows for precise control over the movement trajectories of objects within videos, enabling the simultaneous generation of multiple video objects with accurate motion control. Additionally, the Q1 model provides control over audio generation, ensuring that audio content is inserted at the correct time according to user instructions.
Explore more exclusive insights at nextfin.ai.
