OpenAI Unveils Sora 2: The Next Big Thing in AI Video Generation
OpenAI has launched Sora 2, a significant update to its video generation model and social app. This new version synchronizes audio and video for the first time, including background sounds, speech, and sound effects. OpenAI compares it to the 'GPT-3.5 moment for video', highlighting its advancements over previous models.
Sora 2 maintains continuity across scene changes and handles multiple-shot sequences seamlessly. The app features a customizable feed using new recommender algorithms that respond to natural language instructions. Users can insert themselves into generated scenes using the 'cameo' feature.
OpenAI plans to release Sora 2 through its API, keeping the earlier Sora 1 Turbo model available. The launch is initially invite-based in the U.S. and Canada, offering free access with generous limits. The model strives to obey the laws of physics, generating realistic outcomes and handling complex physical interactions. ChatGPT Pro subscribers gain access to an experimental higher-quality version, Sora 2 Pro.
Sora 2, with its synchronized audio and improved features, is set to enhance user experience in AI-generated video creation and sharing. Its launch, though initially invite-based, promises free access and generous limits, making it accessible to a wide audience.
Read also:
- Mural at blast site in CDMX commemorates Alicia Matías, sacrificing life for granddaughter's safety
- Increased energy demand counters Trump's pro-fossil fuel strategies, according to APG's infrastructure team.
- AI-Powered Transportation Stock's Possible Challenge to Tesla's Autonomous Dreams?
- Consumer Watchdog Warns Against Unlimited Expansion of Waymo, Cruise Robotaxis in San Francisco
