OpenAI unveils Sora, a text-to-video model that can generate videos up to a minute long based on text input. It can create realistic and imaginative videos from text instructions. It uses a combination of text and image generating tools in a diffusion transformer model.

Key takeaways

Sora can generate videos with a resolution of up to 1920 × 1080 pixels, and in a variety of aspect ratios, while Lumiere is limited to 512 × 512 pixels3.

The tool appears to be among the most advanced to date, and its impact will be profound, according to experts.