Adobe has expanded its Firefly family of creative generative AI models to video, hailing it as the first publicly available video model designed to be commercially safe. The company has also added new capabilities to its Image, Vector and Design models.
► More control over creation and editing
► Generates video and images from text prompts
► Enhanced image, vector and design models also added
Features of the video model include Generative Extend, which enables users to extend clips to cover gaps in footage, smooth out transitions, or hold on shots longer. The Text to Video & Image to Video feature provides improved creation and control of video clips from text prompts.
The Firefly Image model can now generate images in seconds – up to four times faster than previous versions models. Improvements in the Vector model enable Adobe Illustrator users to apply recolouring and ‘text to pattern’ styles to existing artwork and designs. Adobe has also previewed Project Concept, a new capability for multiplayer, collaborative, creative concept development that gives users the ability to revise images in real time.
Firefly can be used with Photoshop, Express, Illustrator, Substance 3D and other apps in the Adobe Creative Cloud, to generate content designed to be safe for commercial use. Adobe claims that since its initial beta release in March 2023, Firefly has been used to generate more than 13 billion images – more than 6 billion over the past six months.
Currently available only in beta, Adobe says it will use initial feedback from creative professionals to refine and improve the model.
