OpenAI Unveils Sora, a Highly Advanced Text-to-Video AI Model
OpenAI introduces Sora, a new artificial intelligence model that generates realistic videos up to a minute long from simple text prompts. The tool remains in a testing phase as experts weigh its creative potential against significant misinformation risks.
OpenAI unveils Sora, a new text-to-video artificial intelligence model that generates highly realistic videos up to a minute long from simple text prompts. The tool creates original footage based on user instructions, producing complex scenes with multiple characters and accurate motion that mimic the physical world.
The AI company keeps Sora out of public reach for now as it gathers early feedback from the AI community. While OpenAI CEO Sam Altman showcases impressive examples like dogs podcasting on a mountain, the company admits the model still struggles with complex spatial details and physics, occasionally generating illogical actions or morphing subjects unnaturally.
This dramatic leap in generative AI sparks a frenzy of reactions online as enthusiasts brainstorm creative applications. However, the hyper-realistic nature of the demonstrations raises immediate concerns about digital disinformation and the potential erosion of human jobs once bad actors or the general public gain access to the technology.