Yesterday, Shengshu Technology, a leading domestic AI video technology provider, officially announced the global launch of its independently developed domestic video model Vidu (visit the official website www.vidu.studio). This release marks the entry of the video creation field into a new era of intelligence. With its unique text-to-video and image-to-video core functions, Vidu provides global creators with an unprecedented creative experience.

Vidu's large model offers two video duration options: 4 seconds and 8 seconds, meeting users' diverse creative needs, and supports up to 1080P resolution, ensuring clear and delicate frames. What's even more exciting is that users can generate a high-quality 4-second video clip in just 30 seconds, greatly improving creative efficiency. In order to make it easier for more users to get started, Shengshu Technology has also launched the Vidu Free Edition and Standard Edition. Free Edition users can enjoy 4-second video generation, ultra-clear image quality, and the ability to process one parallel task. The Standard Edition further unlocks advanced features such as 8-second video generation, commercial authorization, ultra-clear watermark-free output, and two parallel tasks, all for only $7.99 per month, offering excellent value for money.

Vidu has also made significant breakthroughs in style diversity. Compared to AI video tools on the market that are mostly limited to realistic styles, Vidu not only perfectly covers realistic, abstract, and other styles but also innovatively introduces an anime style option. This feature not only ensures a high level of consistency in the anime style but also effectively avoids common problems such as screen jitter and style changes in the "anime-ization" process of traditional video generation tools, bringing a smoother and more stable visual experience to anime enthusiasts and creators. In addition, whether it's science fiction, western, romance, or animation themes, Vidu can accurately capture and generate film-standard visual clips, making every work full of texture and imagination.

In the field of "image-to-video," Vidu also demonstrates powerful innovation capabilities. Its unique character consistency function allows users to upload portraits or custom character images and, through simple text descriptions, allow the characters to freely move and perform various actions in any scene. This feature not only simplifies the complex process of video production and saves time and cost in character design and adjustment but also provides unlimited creative space for creators, making video creation more free and flexible.

Vidu also has powerful text understanding and generation capabilities, accurately recognizing and presenting elements such as letters and numbers in prompt words, and generating corresponding text effects. For advanced camera language such as first-person perspective and time-lapse photography, Vidu can also easily express them. Users only need to use detailed prompt words to achieve precise control over the video content, making the creation more intuitive.

Since its establishment in March 2023, Shengshu Technology has gathered top talents from the Tsinghua University Institute of Artificial Intelligence, and its core team has accumulated deep experience and technical reserves in Bayesian machine learning and multimodal large models. Zhu Jun, the company's chief scientist and a professor at Tsinghua University, said, "Vidu's rapid rise is due to the team's relentless pursuit of technological innovation and long-term accumulation. In particular, our independently developed U-ViT architecture, as the world's first fusion of Diffusion and Transformer architecture, provides Vidu with powerful technical support and unlimited possibilities."

With the global launch of the Vidu large model, Shengshu Technology is leading a profound transformation in the field of video creation. In the future, Shengshu Technology will continue to deepen AI video technology and bring more surprises and possibilities to global creators, jointly opening a new chapter in video creation.