Shengshu Technology releases multimodal video generation model Vidu Q1

On March 29th, at the keynote speech of the Zhongguancun Forum's Artificial Intelligence Day, Zhu Jun, Vice Dean of the Tsinghua University Institute of Artificial Intelligence and Founder and Chief Scientist of Shengshu Technology, announced that Shengshu has released its latest multimodal video generation model, Vidu Q1, which will be globally launched in April. According to the introduction, the Q1 model focuses on controllability compared to its predecessor, allowing for precise control over the motion trajectories of objects within the video and the simultaneous generation of multiple video objects with accurate control. In addition, the Q1 model can also control audio generation, ensuring that audio content is inserted at the appropriate time according to user instructions