A major milestone in AI-driven video creation has been reached as a Chinese AI video generator demonstrated the ability to produce a 4-second video clip at 512p resolution in just 10 seconds.
ShengShu Technology, a Beijing-based artificial intelligence company, unveiled its revolutionary video generation model, Vidu 2.0, which builds on its predecessor to achieve unprecedented speed and efficiency in video production. The announcement was made through China’s state media, Xinhua News, on Monday.
The newly enhanced Vidu 2.0 not only generates 4-second videos at impressive speeds but also stands out for its cost-effectiveness. The model can create a full minute of video content for a mere $0.33, making high-quality video generation more accessible to businesses and creators alike.
Historically, while advancements in AI-driven video models have improved video quality, the time required for rendering remained a significant hurdle. Many older models required users, particularly those on free plans, to endure hours-long waiting periods for the completion of a single clip.
The introduction of Vidu 1.0 in July 2024 marked a transformative moment in the industry. This earlier version drastically reduced video creation time to under 30 seconds, paving the way for widespread adoption. Within just 100 days of its release, Vidu 1.0 had amassed a user base of over 10 million globally, setting a benchmark for rapid and efficient video generation.
Vidu 2.0 represents the next stage of this evolution, addressing user demands for both speed and affordability while maintaining exceptional video quality. This innovation positions ShengShu Technology as a frontrunner in the highly competitive AI video generation landscape, with potential implications for industries ranging from entertainment to digital marketing.
