Model from ChatGPT maker ‘simulates physical world in motion’ up to a minute long based on users’ subject and style instructions
OpenAI revealed a tool on Thursday that can generate videos from text prompts.
The new model, nicknamed Sora after the Japanese word for “sky”, can produce realistic footage up to a minute long that adheres to a user’s instructions on both subject matter and style. According to a company blogpost, the model is also able to create a video based on a still image or extend existing footage with new material.
About Author
More Stories
Boeing production in 2024 expected to be less than half of rival Airbus
Apple asks investors to block proposal to scrap diversity programmes
Axos Financial: how the US bank became one of Trump’s biggest backers