介绍:
文生视频大模型 text-to-video large AI model
4月27日，2024中关村论坛年会上首次发布我国自研的具“长时长、高一致性、高动态性”特点的文生视频大模型Vidu。这一视频大模型由清华大学联合北京生数科技有限公司共同研发，可根据文本描述直接生成长达16秒、分辨率高达1080P的高清视频内容。
Vidu, a text-to-video large AI model capable of creating a 16-second, high-definition video in 1080p resolution with a single click, was unveiled on April 27 at the 2024 Zhongguancun Forum. Developed by Tsinghua University and Chinese AI firm ShengShu Technology, Vidu is China's first video large AI model with "extended duration, exceptional consistency and dynamic capabilities".
