Shengshu AI, a burgeoning Chinese start-up, has introduced Vidu, its innovative text-to-video tool now available to users worldwide. Supporting both Chinese and English text prompts, Vidu broadens its reach and allows users to create short video clips of four or eight seconds directly from its official website. This positions Shengshu alongside other key players in the industry, such as Zhipu AI and Kuaishou Technology.
Since its debut in April, Vidu has distinguished itself with its speed, generating a four-second clip in just 30 seconds, making it one of the fastest tools on the market. The technology is built on Shengshu’s proprietary architecture, U-ViT, detailed in a research paper authored by Zhu Jun, the company’s chief scientist and a professor at Tsinghua University. The involvement of Tsinghua alumni in Shengshu’s leadership team underscores the university’s influential role in advancing AI in China.
A notable feature of Vidu is its character-to-video function, which allows users to animate both real and fictional characters through straightforward text prompts. This opens doors for future commercial applications in animation and content creation. Zhang Xudong, Shengshu’s Product Director, anticipates further advancements that will enable users to animate multiple characters and scenes, merging AI tools with traditional industries.
Shengshu has garnered substantial investment, securing tens of millions of dollars from prominent backers including Qiming Venture Partners, Baidu, Ant Group, and the Beijing AI Industry Investment Fund. This robust financial backing highlights the strong belief in Shengshu’s potential to become a leader in AI video generation and positions it as a formidable competitor to OpenAI’s Sora.
