Difficulty: Summiteer (Level 3)
China has come up with its own text-to-video artificial-intelligence (AI) tool called Vidu that can produce videos no longer than 16 seconds. Its videos are shorter compared to Sora’s, a similar model from US company OpenAI that can create 60-second videos.
Vidu was launched last month by start-up Shengshu Technology in a joint effort with the Beijing-based Tsinghua University. The model can make videos with 1080p resolution based on simple text prompts.
“Vidu is the latest achievement of self-reliant innovation, with breakthroughs in many areas,” said Zhu Jun, chief scientist at Shengshu who is also deputy dean at Tsinghua’s Institute for AI.
Zhu announced the model at the Zhongguancun Forum held in the Chinese capital. He added that the model could also comprehend “Chinese elements”.
During the model’s unveiling, Shengshu released several demo clips, including one featuring a panda playing the guitar while sitting on grass and another of a puppy swimming in a pool. Both clips showed vivid details.
