OpenAI announced the Sora tool that generates video from text. This tool is not expected to integrate with ChatGPT at first. However, we may encounter such a surprise with ChatGPT 5. But what kind of features does Sora, a tool for generating video from text through artificial intelligence, have?
OpenAI’s text-to-video AI tool Sora
Paving the way for artificial intelligence, OpenAI has introduced another important tool. This AI tool called Sora comes with the ability to produce videos based on commands given via text. In fact, AI tools with such features appeared before Sora.
Sora has the ability to create one-minute videos based on given commands. These highly detailed videos are also visually very realistic. The artificial intelligence tool that generates videos from text does not only focus on what the user wants with the command. Accordingly, the AI tool also has the ability to understand how the scene described exists in the physical world.
Prompt: “A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. she wears a black leather jacket, a long red dress, and black boots, and carries a black purse. she wears sunglasses and red lipstick. she walks confidently and casually.… pic.twitter.com/cjIdgYFaWq
— OpenAI (@OpenAI) February 15, 2024
Sora can interpret commands more realistically thanks to its deep understanding of language. In this sense, artificial intelligence videos produced by Sora have a much more realistic structure. Sora also has the ability to create multiple different shots that continue the characters and visual style within a single video.
Another one of Sora’s features is that it is not limited to producing videos only from text. Accordingly, the artificial intelligence tool is also capable of producing video from a photo. Sora also has the ability to expand an existing video and fill in missing frames.
OpenAI founder and CEO Sam Altman started sharing Sora videos on X according to commands from users. The videos draw attention especially with their realistic details.
Sora is currently available to OpenAI red team members. This means that for the time being, you cannot use the function of producing videos with artificial intelligence on the Sora page, except for watching existing videos. OpenAI explained that for the time being, the AI tool may have difficulty simulating very complex scenes. What is meant here is that Sora may miss some detail continuities.
