Odyssey, a startup founded about a year ago, has announced the development of generative visual artificial intelligence that reaches Hollywood-level standards. This new model aims to create stunning cinematic scenes and characters while ensuring they are free of errors. According to the company, its model distinguishes itself from text-to-video conversion tools by allowing users full and precise control over every aspect of the scene they wish to create.
Jeff Hawk, one of the company's founders, explained that if "ChatGPT" produces text that cannot be edited by the user, it won’t be useful. This indicates that Odyssey is effectively seeking to empower users. The company is developing multiple generative models that enable users to control various aspects of video, capable of creating high-quality materials with stunning lighting and accurate movement. If achieved successfully, users will be able to easily generate stunning videos.
Oliver Cameron, co-founder and CEO of the company, expressed hope in delivering error-free and stunning visuals for filmmakers. The company has secured $9 million in funding from investors to achieve this goal. Cameron believes this technology will be beneficial in producing films, television shows, and even video games.
The approach taken in creating this generative AI video, which could challenge the likes of Sora, Luma Labs Dream Machine, and Runway, largely stemmed from self-driving vehicles, according to Hawk. This is because self-driving cars have had to push the latest technologies in generative visual AI to power them and have helped expand performance using real-world data. Additionally, self-driving cars require simulations with accurate physics.
