China-developed text-to-video large AI model unveiled in Beijing

: 0 Comment(s)Print E-mail Xinhua, April 28, 2024

Adjust font size:

A woman walks past an art installation at the Zhongguancun International Innovation Center, venue for the 2024 Zhongguancun Forum (ZGC Forum) Annual Conference, in Beijing, capital of China, April 25, 2024. [Photo/Xinhua]

Vidu, a text-to-video large AI model capable of creating a 16-second, high-definition video in 1080p resolution with a single click, was unveiled on Saturday at the 2024 Zhongguancun Forum in Beijing.

Developed by Tsinghua University and Chinese AI firm ShengShu Technology, Vidu is China's first video large AI model with "extended duration, exceptional consistency and dynamic capabilities."

As a large AI model developed in China, Vidu is able to understand and generate Chinese content such as the panda and the loong, or the Chinese dragon, according to Zhu Jun, deputy director of the Tsinghua Institute for Artificial Intelligence.

The company said that Vidu's core architecture was proposed as early as in 2022.

Follow China.org.cn on Twitter and Facebook to join the conversation.
ChinaNews App Download