On March 29, at the keynote speech of the Artificial Intelligence Day of the Zhongguancun Forum, Zhu Jun, deputy dean of the Institute of Artificial Intelligence of Tsinghua University, founder and chief scientist of Shengshu-ai, announced that Shengshu-ai released the latest multi-modal video generation model Vidu Q1, which will be online globally in April. According to reports, the Q1 model is mainly controllable compared with the previous generation model, and the model can ensure the accurate control of the motion trajectory of the object in the video, and can generate multiple video objects at the same time and accurately control. In addition, the Q1 model controls audio generation, ensuring that audio content is inserted at the right time according to user instructions
Share this post
Shengshu-ai releases Vidu Q1, a multimodal video generation model
Share this post
On March 29, at the keynote speech of the Artificial Intelligence Day of the Zhongguancun Forum, Zhu Jun, deputy dean of the Institute of Artificial Intelligence of Tsinghua University, founder and chief scientist of Shengshu-ai, announced that Shengshu-ai released the latest multi-modal video generation model Vidu Q1, which will be online globally in April. According to reports, the Q1 model is mainly controllable compared with the previous generation model, and the model can ensure the accurate control of the motion trajectory of the object in the video, and can generate multiple video objects at the same time and accurately control. In addition, the Q1 model controls audio generation, ensuring that audio content is inserted at the right time according to user instructions
.