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.

AI-powered measurement: Proving ad impact in a fragmented media landscape
AI-powered ad measurement is helping brands navigate complexity, attribute value more accurately, and make smarter, real-time decisions about where to spend. David Howell reports.

NAB NY preview: Political backdrop casts long shadow over TV innovation
Buffeted by economics and squeezed by Big Tech, the last thing America’s broadcasters wanted was to have their news operations muzzled or business threatened with political interference, yet that’s the realpolitik of the US TV entering NAB Show NY.

Immersive Flashback captures Bastille Day for VR
Bastille Day is one of France’s most recognisable national events, combining military parades, aerial flyovers and state ceremonies watched around the world. For the first time, the celebration was captured as an immersive production.

Esports on a budget: Bringing production to the classroom
Two UK-based brands are working together to make esports production more accessible to students across the country.

MXL: Transforming production with open collaboration and shared memory
The launch of the MXL project under the Linux Foundation looks to provide a pivotal shift in how media workflows operate, solving fundamental inefficiencies and incompatibilities that have long plagued digital media infrastructure.