Adobe announced Monday that it has begun publicly distributing an AI model that can generate videos from text prompts, joining the growing number of companies trying to disrupt film and television production using the generative artificial intelligence.
The Firefly video model, as the technology is called, will compete with OpenAI’s Sora, which was introduced earlier this year, while TikTok owner ByteDance and Meta Platforms also announced their video tools during of the last few months.
Facing much larger competitors, Adobe has focused on creating models trained on data it owns the rights to use, ensuring that the results can be legally used in commercial work.
San Jose, Calif.-based Adobe will begin opening the tool to people who have signed up to its waitlist, but has not given a general release date.
Adobe has not yet announced any customers using its video tools, but said Monday that Gatorade, a company owned by PepsiCo, would use its image generation model for a site where customers can order personalized bottles, and that Mattel used Adobe tools to design the packaging for its line of Barbie dolls.
For its video tools, Adobe has sought to make them practical for everyday use by video creators and editors, with a particular focus on ensuring that footage blends in with conventional footage, said Ely Greenfield, director of video production. Adobe technology for digital media.
“We really focus on fine control, teaching the model concepts that video editors and videographers use, like camera position, camera angle, camera movement,” Mr. Greenfield in an interview with Reuters.
