Vidu, co-released by Shengshu Technology and Tsinghua University, is the first long-duration, high-consistency, and high-dynamic video large model in China. This model utilizes a proprietary architecture, U-ViT, which merges Diffusion with Transformer, supporting one-click generation of up to 16-second videos with 1080P resolution. Vidu not only simulates the real physical world but also boasts rich imagination, characteristics such as multi-camera generation, and high temporal-spatial consistency. Its rapid breakthrough is attributed to the team's long-term accumulation in Bayesian machine learning and multimodal large models, as well as numerous original achievements. Vidu's launch represents the sustained innovative capabilities and leadership of Shengshu Technology in the multimodal native large model field. Looking to the future, its flexible architecture will be able to accommodate a wider range of modalities, further expanding the boundaries of multimodal general capabilities.