Adobe Firefly" is a family of creative generative AI models developed by Adobe. These models use deep learning techniques to generate visual content, such as images, illustrations, and animations, based on user input and preferences.
The Firefly models were created as part of Adobe's ongoing efforts to explore the potential of AI in the creative process. They aim to offer designers, artists, and other creatives new tools and capabilities for generating and manipulating visual content. Adobe Firefly models use a combination of generative adversarial networks (GANs) and reinforcement learning techniques to learn from existing visual data and generate new content.
The Firefly models are still in development, but Adobe has shared some of their initial research and results in this area. They have also released a few experimental tools and prototypes that leverage Firefly technology, such as Project Avatar, which allows users to generate 3D avatars using AI.
Bringing Generative AI into Creative Cloud with Adobe Firefly
Firefly is a major step forward. Our first Firefly model focuses on the creation of images and text effects. It is particularly valuable to those seeking to generate content for commercial use because it is trained on hundreds of millions of professional-grade, licensed images in Adobe Stock along with openly licensed content and public domain content where the copyright has expired.
We’ve augmented the model with a powerful style engine, to help you explore the generative capabilities and create photos, art, graphics and text effects with impressive style, color, tone, lighting and composition controls. Everything is designed, from the ground up, to be embeddable into your existing workflows across Adobe Creative Cloud, Document Cloud, Experience Cloud and Adobe Express. Adobe is also planning to make Firefly available via APIs on various platforms to enable customers to integrate into custom workflows and automations.
