Adobe says it has worked closely with professional video creators to advance the Firefly Video Model with a particular emphasis on generative editing, reports Adrian Pennington.
Adobe has progressed its generative AI video product with further tools to enhance the editing process launching in beta.
First previewed earlier this year, the Firefly video model’s capabilities launching in beta this week are designed to help video editors fill gaps in a timeline and add new elements to existing footage.
“Video is hard,” says Alexandru Costin, Vice President, Generative AI and Sensei at Adobe. “We’ve been working on it for a while but we weren’t happy with the quality. Our research department has done wonders to handle 100 times more pixels, 100 times more data using thousands and thousands of GPUs to make sure we master the research. We’re now proud of the quality we’re delivering.”...
You are not signed in
Only registered users can read the rest of this article.
From screens to spaces: The rise of immersive experiences in live events
From AR-powered sports coverage to immersive theatre and AI-driven fan engagement, broadcasters, organisers, and rights holders are rethinking how live experiences are created and extended beyond the event itself.
SVOD vs AVOD: The reinvention of live sports viewing
The live sports landscape is the crown jewel of entertainment, and as it evolves, streaming platforms are driving its next phase of growth.
Content Everywhere: The long and the short of it
Short-form video platforms such as TikTok, Instagram Reels, and YouTube Shorts have transformed how audiences consume content. According to recent data from YouGov, rather than replacing traditional viewing, short-form clips are becoming an important step in the viewing journey, helping audiences discover shows and inspiring them to tune in.
Hybrid by design: How immersive tech is transforming remote collaboration
From shared virtual spaces and volumetric media to real-time engines and cloud rendering, broadcast and proAV teams are moving beyond simple connectivity towards collaboration that feels genuinely co-located.
Creator takeover at MPTS: “You’re competing for tiny slices of attention”
Exhibitor and conference sessions still nestle deep-tech dives about compression alongside tutorials on podcasting, but this no longer feels incongruous. Adrian Pennington reports.


.jpg)
