Can AI really generate photorealistic videos from a text prompt?
Type a sentence, get a Hollywood-quality video. Sora made jaws drop worldwide.
The answer
OpenAI's Sora, previewed in February 2024 and released to the public in December 2024, is a diffusion-transformer model that generates up to 60-second videos at 1080p resolution from text descriptions. Sora treats video frames as spacetime patches - similar to tokens in language models - allowing it to understand physical dynamics like fluid motion, reflections, and object permanence. While the results are striking, limitations remain including occasional physics violations like objects morphing or disappearing, and the broader release sparked intense debate about deepfakes and creative industry disruption.
Source: OpenAI
- openai
- sora
- video generation
- generative ai
More from AI & Machine Learning
- What radical question did Alan Turing ask in 1950 that launched the entire field of artificial intelligence?
- Can a machine fool you into thinking it's human - and does that mean it's truly intelligent?
- What happened at a small Dartmouth workshop in 1956 that gave artificial intelligence its name?
- How did a 1958 invention called the Perceptron convince people that machines could learn like brains?
- Could a 1966 chatbot really make people believe they were talking to a therapist?
- What was the first robot that could 'reason' about its own actions?