Monday Adobe Announce Firefly Video Model, a new AI-powered text-to-video tool that can create new videos from written prompts. It joins similar offerings from OpenAI, Runway, Google, and Meta in an increasingly crowded field. Unlike the competition, Adobe claims that the Firefly Video Model was trained exclusively on licensed content, potentially avoiding the ethical and copyright issues that plague other generative AI tools.
Given the roots of licensed training data, Adobe calls… Firefly video template “The first publicly available video model designed to be commercially secure.” However, the San Jose, California-based software company has not announced a public release date, and during the beta testing period, it is only giving access to people on a waiting list.
Adobe Firefly video mockup video, provided by Adobe.
In the works since at least April 2023, the new model is based on technologies developed by Adobe for its Firefly photomontage models. Like the text-to-image builder, which the company later integrated into Photoshop, Adobe hopes to target the Firefly Video Model to media professionals, such as video creators and editors. The company claims that its model can produce footage that blends seamlessly with traditionally created video content.
“Certified food guru. Internet maven. Bacon junkie. Tv enthusiast. Avid writer. Gamer. Beeraholic.”
More Stories
Nintendo is launching a music app with themes from Mario and Zelda, and more importantly, a Wii Shop channel
The Google Pixel Tablet 3 will take another step towards replacing your laptop
Apple still excels at building the best computers