Get the latest tech news

OpenAI’s newest model Sora can generate videos — and they look decent

OpenAI has been working on a video generation model, Sora. The results aren't perfect -- but they're among the better examples we've seen.

“Sora has a deep understanding of language, enabling it to accurately interpret prompts and generate compelling characters that express vibrant emotions,” OpenAI writes in a blog post. And these videos maintain reasonable coherence in the sense that they don’t always succumb to what I like to call “AI weirdness,” like objects moving in physically impossible directions. The model may also confuse spatial details of a prompt, for example, mixing up left and right, and may struggle with precise descriptions of events that take place over time, like following a specific camera trajectory.”

Get the Android app