Biotech and Tsinghua University jointly released China’s first long-duration, highly consistent, and highly dynamic video model: Vidu.
This model is regarded as the first video model in China to reach Sora level.
Vidu not only simulates the real physical world, but also has rich imagination and supports multi-shot generation and high spatio-temporal consistency.
The Vidu model combines Diffusion and Transformer technologies to innovatively develop the U-ViT architecture.
It can generate high-definition video content with a single click of up to 16 seconds and a resolution of up to 1080P.
In official sources, a video example is shown, which shows “a boat in the studio heading towards the camera”, showing the realistic effect of the boat and the waves.
Beijing Shengshu Technology Co., Ltd.(referred to as “Shengshu Technology”) was established in March 2023. The core team members are from the Institute of Artificial Intelligence of Tsinghua University. In addition, it brings together top talents from well-known technology companies such as Alibaba, Tencent, and Byte., is the world’s leading deeply generative algorithm research team, with the bottom-level innovative research and development capabilities of diffusion probability models.
The company is committed to building the world’s leading multimodal model, integrating multimodal information such as text, images, video, and 3D, and exploring the commercial empowerment of generative AI in art design, game production, post-film and television, content social and other scenarios. AI enhances human creativity and productivity.
If you want to learn more, you can click on the link below the video.
Thank you for watching this video. If you like it, please subscribe and like it. thank
Official website:https://www.shengshu-ai.com/home
Video: