Washington, February 16 (QNA) - OpenAI, a research lab specializing in artificial intelligence, has unveiled a new tool called Sora that can generate videos from text descriptions.

The tool can create realistic videos, as well as videos inspired by still images. It can also add visual content to existing videos.

Sora can generate videos in a variety of styles, including photorealistic and black-and-white animation. Videos can be up to one minute long, which is significantly longer than most other text-to-video models.

"The model has a deep understanding of language, enabling it to accurately interpret prompts and generate compelling characters that express vibrant emotions. Sora can also create multiple shots within a single generated video that accurately persist characters and visual style," the company wrote in a blog post.

"By providing a short or detailed description or a still image, the Sora model can generate movie-like scenes at 1080p resolution with multiple characters, different types of motion, and background details," the company said.

The company added that Sora can also extend existing videos, doing its best to fill in the missing details. (QNA)