【#Tech24H】Beijing-based AI company Shengshu Technology released the first preview version of its new-generation flagship video generation model, Vidu Q4 Preview. The model has been further upgraded in capabilities such as character performance, cinematic language, and complex visual effects. It supports up to 15 reference images and 3 reference audio clips, as well as 2K and 4K output. As multimodal large models continue to evolve, China’s AI video industry is accelerating from capability demonstrations toward actual production. Continuous optimization in generation quality, controllability, inference efficiency, and usage cost is expected to provide more efficient digital content production tools for fields such as film and television, animation, advertising, e-commerce, and cultural communication.[ By Zhang Liyan | Tang Ruohan ]