Adobe on Monday announced the public rollout of its innovative AI model capable of generating video content from text prompts, positioning itself within the burgeoning landscape of generative artificial intelligence aimed at revolutionising film and television production.
The newly launched Firefly Video Model will compete with existing technologies such as OpenAI’s Sora, introduced earlier this year, alongside offerings from TikTok’s parent company, ByteDance, and Meta Platforms, both of which have recently revealed their own video generation tools.
Strategic focus on legality and user experience
Amidst formidable competition, Adobe is prioritising the development of models trained on proprietary data, ensuring that the resulting output can be legally utilised in commercial ventures.
Based in San Jose, California, the company will begin granting access to its video generation tool to users who have registered on a waiting list, although a definitive general release date has yet to be announced.
While Adobe has not disclosed any specific clients utilising its video technology, it has confirmed partnerships with brands such as Gatorade, owned by PepsiCo, which plans to implement its image generation model for a customisable bottle ordering site.
Read More: PTA appoints US consultancy for Pakistan’s upcoming 5G auction
Furthermore, toy manufacturer Mattel has employed Adobe tools for the design of packaging related to its Barbie doll line.
Meanwhile, Adobe’s chief technology officer for digital media Ely Greenfield emphasised the company’s focus on practicality for everyday video creators and editors. The goal is to ensure that generated footage seamlessly integrates with traditional video content.
“We really focus on fine-grain control, teaching the model the concepts that video editors and videographers use – things like camera position, camera angle, camera motion,” Greenfield stated in an interview with Reuters, highlighting Adobe’s commitment to enhancing the user experience in video production.
