OpenAI launched a new software: Sora. The software generates short videos starting from a simple text: here’s how it works.
OpenAI, the company behind ChatGPT, announced Sora, a powerful new AI-powered software for creating videos up to one minute long. The official communication arrived a few days ago, on February 15, through a note published on the San Francisco-based company’s website, together with some demonstration videos. Here’s what we know so far.
What is Sora and how does it work
Sora is a software designed by OpenAI capable of creating short films starting from a text, an image or a video clip. In practice, to use it a user must enter a request - also known as a prompt - which is processed thanks to artificial intelligence and returned in the form of a video.
On the functioning of the new software, OpenAI stated on its official site:
Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background. The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world. 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 videos posted on the company’s website confirm that these are very "credible" clips, particularly considering that the app is still in its first version and therefore has ample room for improvement.
How to try Sora
Sora is currently available only to a small number of experts selected by OpenAI for a preview trial. These are primarily artists and developers tasked with providing the company with constructive feedback on how to improve the product.
Trying it for others is currently complex, but not impossible. A few days ago, in fact, OpenAI CEO Sam Altman, asked his followers on share them with users.
Some lucky people were able to see their requests take shape through the company’s new artificial intelligence.
To date, in short, the only way users have to satisfy their curiosity is to comment on Altman’s post in the hope that he will choose their description. Alternatively, you will need to wait for the new application to be released.
Can Sora be dangerous?
Can Sora be dangerous? Like all applications of this type it is obvious that it potentially presents risks depending on how it is used. The main danger is represented by deep fakes, i.e. content manipulated via AI to make it appear as if a person is saying or doing something they never said or did.
In a year full of elections around the world, tools like Sora can be dangerous due to the impact they can have on the world of information and public opinion. Some deepfakes spread in the past - think of the one depicting Pope Francis in a white down jacket or Donald Trump being arrested - had already raised quite a bit of controversy. Sora, if not used properly, could lead to the creation of similarly harmful content.
OpenAI also seems to be aware of these risks, writing on its website: "Despite extensive research and testing, we cannot predict all of the beneficial ways people will use our technology, nor all the ways people will abuse it. That’s why we believe that learning from real-world use is a critical component of creating and releasing increasingly safe AI systems over time.”
Original article published on Money.it Italy 2024-02-20 17:06:40. Original title: Sora: cos’è, come funziona e come usare la nuova IA di OpenAI per creare video
