China has announced the unveiling of “Vidoo”, an advanced model of artificial intelligence that transforms texts into video clips, during the 2024 Zhongguancun Forum in Beijing. This system is capable of producing 16-second videos in high quality and up to 1080 pixels resolution with just one click.
“Vidoo”, the result of a collaboration between Tsinghua University and the Chinese company Shengshuo specializing in artificial intelligence technologies, represents the first leading model in the field of video-specific artificial intelligence, distinguished by features including expanded time range and exceptional precision, along with dynamic and interactive capabilities.
As an advanced and massive artificial intelligence system developed in China, “Vidoo” has the ability to comprehend Chinese content such as pandas, Chinese dragons, and interpret them, according to Chou Jeon, the Deputy Director of the Artificial Intelligence Institute at Tsinghua University.
The company stated that a proposal has been made to establish the basic structure of the model in early 2022.
