Vidu Introduces Subject Consistency in AI Video Creation

BEIJING,Sept. 11,2024 --Vidu,a text-to-image video multimodal model developed by ShengShu Technology,today has introduced a new subject consistency (Subject to Video) feature.

With support for plants,animals,and other non-human forms,this pioneering capability opens new creative horizons for filmmakers,marketers,and content creators,giving them the ability to explore greater use of AI in their production process. Whether users upload images of bags,monsters,or specific styles,these subjects will remain consistent throughout the generated video. This feature ensures that each element remains coherent and coordinated in terms of style,forms,colors,narrative,roles,and scenes,delivering a unified and complete visual and narrative experience,while maintaining high resolution.

This update follows closely on the heels of Vidu's official release just a month ago,underscoring the company's commitment to staying ahead in the competitive AI video generation market. Vidu has made significant strides in speed,generating a 4-second clip in just 30 seconds with 1080p high resolution. Vidu empowers users to animate characters or scenes,enhancing storytelling capabilities—particularly valuable for creators looking to integrate existing artwork or photos into video narratives,transforming their artistic concepts into dynamic and engaging visual experiences.

"This achievement is a testament to the incredible dedication and innovation of our team," said Jiayu Tang,Cofounder and CEO of Shengshu Technology. "We're proud to bring this feature to market and believe it will significantly enhance how our users interact with and utilize AI in their creative processes."

Vidu is available at vidu.studio. The company is committed to continuously developing Vidu,consistently improving its capabilities to meet and exceed industry demands.

About Shengshu Technology

Founded in 2023,Shengshu Technology specializes in multi-modal large models,and is one of the earliest teams globally to engage in diffusion probability model research. Shengshu introduced the world's first new technical framework,U-ViT,which explores the fusion of Diffusion Models and Transformer architectures for various multimodal generation tasks in 2022. The company is actively exploring the commercial potential of generative AI in areas such as art design,game development,film post-production,and content socialization. Shengshu's ultimate vision is to use this multimodal model to enhance human creativity and productivity through AI. Shengshu's product,Vidu,was launched globally in July.

Contact

Media Relations

Shengshu Technology

[email protected]