China's first fully self-developed video model, Vidu, created by Shengshu Technology and Tsinghua University, introduces the 'Subject Reference' feature to ensure character consistency in AI-generated videos. Users can upload images, and Vidu maintains consistency across various scenes. This free feature marks a new era in AI video creation, aiming for precise multi-subject interaction and style uniformity. Director Shi Yuxiang praised its enhanc....

Recently, the Xiamen police uncovered a case involving the use of AI technology to create fake videos. A 32-year-old man, Ren (from Hubei), was arrested for allegedly disseminating false information. Ren generated fake content and images and then created a video using AI technology, which he posted on Today’s Headlines. The video spread rumors about an elderly person being beaten in Guangdong and their grandson committing suicide by jumping into a river, attracting widespread attention. His aim was to increase followers and traffic for profit. Ren admitted that it only takes two to three minutes to create videos using AI technology. The police have taken criminal coercive measures against Ren; this incident serves as a warning.

Recently, the AI video generation platform Runway announced that their latest product, Gen-3 Alpha, has been opened for testing to a select group of users. Compared to the previous generation, Gen-3 Alpha has achieved significant improvements in aspects such as lighting, quality, composition, text semantic restoration, physical simulation, and action consistency/continuity, making it a product that can rival OpenAI's Sora. If you are also interested in Gen-3 Alpha and would like to experience it

AI-generated videos are becoming increasingly realistic, making it difficult for humans (and current detection systems) to distinguish between real and fake videos. To address this issue, researchers at Columbia University's School of Engineering, led by computer science professor Junfeng Yang, have developed a new tool called DIVID, which stands for DIffusion-generated VIdeo Detector, to detect AI-generated videos. DIVID was released earlier this year by the team.

Pika is a startup known for its AI-driven platform for editing and generating videos. The company has raised $55 million in funding led by Lightspeed Venture Partners. Pika has launched its AI-powered video editing tool platform, Pika 1.0, which features the ability to extend and transform video styles as well as AI-edit video content. Investors are optimistic about Pika's prospects and differentiated advantages in the field of AI-generated videos.

AI video generation startup Runway has launched a new 'Watch' feature that allows users to share AI-generated videos. Runway aims to build a community of artists and filmmakers, supporting them in their AI-generated works. The CEO of Runway emphasizes that AI-generated videos require human creativity and control.