Two self-driving car company veterans launched Odyssey, an Artificial Intelligence (AI) startup, aiming to create ‘Hollywood-grade video tools for professional filmmakers and animators.’
“We’re building Hollywood-grade visual AI, where beautiful scenery, characters, lighting, and motion can be both generated and directed,” Odyssey CEO and co-founder Oliver Cameron said on X.
Cameron and fellow co-founder Jeff Hawke have prior experience building AI for their former companies, Voyage and Wayve, respectively.
Odyssey projects that it will offer more fine-grain control over the outputs of the AI model, with co-founder Hawke saying, “We believe this technology is what comes after text-to-video.”
Odyssey promises to break the mold of AI-generating video tools, offering users complete creative control over the final output. Co-founder Hawke says, “We believe this technology is what comes after text-to-video.”
In a thread on X, Hawke stated that Odyssey allows users to fine-tune their control over the AI model’s outputs, arguing that if OpenAI’s ChatGPT gave users output that they couldn’t edit, they wouldn’t use it.
“But that’s how text-to-video works today, where the model output is a fully-baked video file that you can’t edit,” the co-founder added, remarking that users must generate all over again if any output variable is off.
Odyssey surpassed this limitation by going beyond a single text-to-video model, instead training models to generate ‘high-quality geometry, photorealistic materials, stunning lighting, and controllable motion.’