The process of using artificial intelligence to generate text and images has become more sophisticated with the advent of AI platforms such as ChatGPT (for text) and Stable Diffusion (for images), so it is only a matter of time before this technology becomes widespread. It was a problem. to video. Now, a New York-based startup has introduced a service that generates crude videos based on short text descriptions.
A company called Runway AI is introducing its service to select testers this week, and is part of a wave of “generative AI” tools that have generated a tremendous amount of buzz over the past few months. The use of AI in film and video production has been around for years, and has even led to the emergence of “deep fake” video, but the process of generating media using text commands has remained a familiar part of the creative community. It can have a big impact.
In a New York Times article, Ian Sansavera, the startup’s software architect, explained how it works by typing in the short description “Quiet river in the woods.” Few minutes.
Early implementations of this technology produced crude, often bizarre, and distorted videos. For example, typing “a bear with a cell phone” will generate a bear shaped like a cell phone. Currently, you can only generate videos up to 4 seconds long. However, like most AI-based services, we expect it to improve rapidly as it collects more data from more users. This is one of the reasons Runway wants to publish the service as soon as possible.
“This is one of the most impressive pieces of technology we have built in the last 100 years,” Runway CEO Cristobal Valenzuela told The Times.
As services like Runway gain momentum and become more sophisticated, the concept of creating professional-looking videos at the touch of a button could become a major concern for anyone in the content creation business. .
“In the old days, to do something remotely like this, you needed a camera. You needed props. You had to have a place. I had to,” Susan Bonser, a Pennsylvania-based author and publisher who has dabbled in generative AI, told The Times. “You don’t have to have anything now. Sit back and imagine.”
Read more in The New York Times.