OpenAI has introduced Sora, a text-to-video AI model to generate videos from text prompts written by the user.
Sora is designed to create complex scenarios, including multiple characters, specific movements, and detailed subjects and backgrounds. The company claims the model understands the physical existence of objects and generates characters with emotional depth. Moreover, the model can create a video from a static image or amend it by adding missing frames or extending it, aside from a few potential issues with complex physics.
Additionally, the model can generate videos of an arbitrary resolution and aspect ratio (up to 1080p), simulating digital worlds that can be used to create video games.
Analyst QuickTake: OpenAI's advancement will likely spur competition among companies offering video generation solutions like Runway, potentially driving further innovation in the space. This technology could open up new avenues for creativity, allowing creators to explore ideas and narratives previously constrained by budget, skill, or technology.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.