Meta has unveiled its latest AI innovation, Movie Gen, a powerful model designed to generate realistic video and audio clips based on user prompts. Positioned as a direct competitor to tools from top media generation companies like OpenAI and ElevenLabs, Movie Gen is set to shake up the industry with its advanced capabilities. Meta shared samples of MovieGen’s impressive creations, showcasing videos of animals swimming and surfing, along with clips that use real photos of people to depict them performing activities like painting on a canvas. In a blog post, Meta highlighted that MovieGen can also produce background music and sound effects that align perfectly with the video’s content, as well as edit existing footage with ease.
According to Meta, videos generated by MovieGen can last up to 16 seconds. The audio can be as long as 45 seconds. Meta also shared data from blind tests showing that MovieGen performs well compared to tools from startups like Runway, OpenAI, ElevenLabs, and Kling. The announcement arrives at a time when Hollywood is grappling with how to use generative AI video technology. Earlier this year, Microsoft-backed OpenAI showcased its product Sora in February. Sora can create feature film-like videos based on text prompts.
Technologists in the entertainment industry are keen to adopt these tools to streamline filmmaking. However, some are concerned about systems trained on copyrighted material without permission. Lawmakers have also raised concerns about the use of AI-generated deepfakes in elections globally, including in the U.S., Pakistan, India, and Indonesia.
Officials from Meta stated that Movie Gen will probably not be made available for developers to use openly. Instead, Meta is collaborating directly with the entertainment community and content creators to explore the applications of MovieGen. The company plans to integrate it into its own products next year. According to a blog post and a research paper released by Meta, MovieGen was built using a combination of licensed and publicly available datasets.
OpenAI has been meeting with Hollywood executives and agents this year to explore potential partnerships involving Sora, but no deals have been finalized. Concerns about the company’s practices grew in May when actress Scarlett Johansson accused OpenAI of using her voice without permission for its chatbot. In September, Lions Gate Entertainment, known for “The Hunger Games” and “Twilight,” announced that it would allow AI startup Runway to access its film and television library for training an AI model. In return, it said that the studio and its filmmakers can use the model to enhance their projects.
- The Wait Is Over: OpenAI Finally Introduced Sora - December 12, 2024
- Google’s AI Video Generator Launches in Private Preview, Ahead of OpenAI’s Sora - December 11, 2024
- Meet Nova: Amazon’s New Family of Multimodal AI Models - December 10, 2024