Vidu（Reference to Image）
API Overview
Vidu is Beijing Shengshu Technology Co., Ltd. in collaboration with Tsinghua University to launch China's first long-duration, highly consistent, and highly dynamic video large model, unveiled on April 27, 2024, at the Zhongguancun Forum Future AI Pioneer Forum. The model features the team's pioneering, globally first-ever Diffusion-and-Transformer hybrid architecture, U-ViT.
Vidu offers three core functionalities—reference-based video generation, text-to-video synthesis, and image-to-video conversion—along with two time-length options: 4 seconds and 8 seconds, delivering resolutions up to 1080P.
Vidu boasts leading advantages in generation speed, consistency, and dynamism, producing a 4-second video in just 10 seconds.
For more information, refer to the official documentation:https://platform.vidu.cn/docs/reference-to-image
API Console
Log in to explore more features! Click to Log In