Vidu Launches AI Video Creation Feature in Beijing on Sept. 11, 2024

On September 11, 2024, Vidu, a text-to-image video multimodal model developed by ShengShu Technology, unveiled a groundbreaking feature called subject consistency. This innovative capability allows users to maintain coherence in style, forms, colors, and narratives throughout their generated videos, regardless of the subjects they upload, such as plants or animals. This feature is particularly beneficial for filmmakers and content creators, enhancing their storytelling abilities by ensuring a unified visual experience. The introduction of subject consistency follows Vidu's official launch in July 2024, highlighting ShengShu Technology's commitment to advancing AI video generation. The model has made significant improvements in speed, capable of producing a 4-second video clip in just 30 seconds at 1080p resolution. This efficiency empowers users to animate characters and scenes, transforming static artwork into dynamic narratives. Jiayu Tang, the CEO of ShengShu Technology, emphasized the dedication and innovation of the team in bringing this feature to market. The company aims to continuously enhance Vidu's capabilities to meet the evolving demands of the industry. By integrating existing artwork or photos into video narratives, Vidu opens new creative avenues for users, allowing them to explore the potential of AI in their production processes. Founded in 2023, ShengShu Technology specializes in multimodal large models and has been at the forefront of diffusion probability model research. The company envisions using its multimodal model to boost human creativity and productivity through AI, with applications spanning art design, game development, and film post-production.