China's first Sora-level text-to-video large model Vidu unveiled

China's first Sora-level text-to-video large model Vidu was unveiled at the 2024 Zhongguancun Forum in Beijing on Saturday, intensifying the artificial intelligence competition globally.

Vidu, developed by Chinese AI firm Shengshu Technology and Tsinghua University, told China Daily that the model can create a high-definition video 16 seconds long and 1080p resolution in just one click.

The company said that it is China's first inaugural video large model with extended duration, exceptional consistency, and dynamic capabilities and is "very close to" the level of Sora.

Sora is a generative AI model developed by the United States' OpenAI earlier this year. With its ability to build realistic and imaginative scenes from text instructions, the model has taken the tech world by storm.

Compared with Sora, Vidu is able to understand and generate Chinese elements such as the panda and dragon.

The company also added that the core architecture of the large model was initiated in September 2022, which was earlier than Sora's adoption of its architecture.