Artificial intelligence has learned to instantly create video from text: a powerful breakthrough

AI has opened up new horizons

Technology company OpenAI is launching a tool that uses artificial intelligence to instantly create video from text. The model from the manufacturer ChatGPT “simulates the physical world in motion” for up to a minute, based on user instructions for theme and style.

Photo: freepik.com

On Thursday, OpenAI introduced a tool that can generate video from text clues, writes The Guardian.

The new model, called Sora after the Japanese word for «sky», can create realistic footage up to a minute long, following the user's instructions in both subject matter and style. According to the company's blog post, the model is also capable of creating video from a still image or augmenting existing footage with new material.

“We teach AI to understand and model the physical world in motion, with the goal of creating learning models that help people solve problems that require interaction in the real world,” says the blog post.

One video included in The number of several initial examples from the company was based on the prompt: «Movie trailer about the adventures of a 30-year-old astronaut wearing a red wool knit motorcycle helmet, blue sky, salt desert, cinematic style, shot on 35mm film, bright colors.» /p>

The company announced that it has opened access to Sora to several researchers and video creators.

Experts will “re-check” product — will test it against OpenAI's terms of service, which prohibit «extreme violence, sexual content, hateful images, celebrity likenesses, or IP of others,» according to a company blog post.

The company provides limited access only to researchers, visual artists and filmmakers, although CEO Sam Altman responded to user queries on Twitter following the announcement with video clips he said were made by Sora. The videos have a watermark indicating that they were made by artificial intelligence.

The company debuted still image generator Dall-E in 2021 and chatbot ChatGPT in November 2022, which quickly gained 100 million users. Other artificial intelligence companies have introduced video generation tools, although these models were only able to generate a few seconds of video footage that often had little relevance to their clues. The tech giants said they are in the process of developing video generation tools, although they have not released them to the general public.

On Wednesday, the company announced an experiment to add deeper memory to ChatGPT so it can remember more of its chats. users.

OpenAI did not disclose how much footage was used to train Sora or where the training videos might have come from, other than to report from the New York Times that the corpus contained videos that were both publicly available and licensed from copyright owners. right The company has been sued multiple times for alleged copyright infringement in training its generative artificial intelligence tools, which digest enormous amounts of material scraped from the Internet and imitate the images or text contained in those data sets.