OpenAI launches the Sora neural network that converts text to video.

OpenAI has introduced a new artificial intelligence model called Sora, which can convert text prompts into videos. With Sora, creating video content is fast and easy. Additionally, it provides several new features, such as Storyboard and Creativity Stream.

The Sora model can create multiple videos and combine them into one using an interactive timeline. Users can also publish their videos, watch examples from other users, and modify them according to their needs.

Introducing Sora, our text-to-video model.Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. “Beautiful, snowy… pic.twitter.com/ruTEWn87vf

— OpenAI (@OpenAI) February 15, 2024

Users can generate videos using text prompts, change the style of the clips using the Remix tool, and combine clips using the Storyboard feature. Sora also has preset styles and the ability to trim videos and choose formats.

Access to video generation through Sora is available for a fee. ChatGPT Plus subscribers can create up to 50 videos per month, while ChatGPT Pro subscribers can create up to 500 videos per month.

It is worth noting that all generated videos come with watermarks and C2PA metadata for protection. OpenAI has also set strict usage rules that prohibit content involving minors, violence, and copyright violations.

With the Sora model, videos can be created quickly and easily. This is a new opportunity provided to OpenAI users. User feedback is important at this stage of the release.

Moreover, research has shown that jokes created by artificial intelligence are funnier than those created by humans. Such videos could create new opportunities and impact the development of various fields.