- Adobe unveiled its latest Firefly Image generative AI (genAI) model, promising greater realism, and improved controls over generated outputs at its Adobe Max event in London.
- The next-generation Firefly model will also be integrated into Photoshop, with several new features coming to the image editor later this year.
- Adobe Firefly is a set of generative AI models used to create and modify content such as photographic style images, it’s accessible as a standalone app, as well as being integrated into Adobe’s Creative Cloud application suite.
The latest iteration of the Firefly AI generative AI model brings improved image quality, more control over outputs, and deeper integration into the Photoshop image editing app.
Also read: Adobe Premiere Pro’s generative AI tools make video editing easier
What is Firefly AI?
Adobe Firefly comprises generative AI models designed for creating and modifying various content types like photographic style images, illustrations, and fonts. Scheduled for release later this year, Firefly will introduce a video-generation model to Premier Pro and a music-generation algorithm. It’s available both as a standalone app and integrated into Adobe’s Creative Cloud suite.
After over a year since its launch, Firefly’s Image model is now in its third iteration, boasting enhancements in image quality, particularly for images featuring people. Improvements include more photo-realistic outputs, better lighting and subject positioning, and enhanced rendering of straight lines and structures for improved image coherence.
Also read: Why did Adobe abandon the deal of the year with Figma?
Power features
Adobe announced that Firefly Image 3 will offer a wider range of output styles for illustrations, photographic art, and vector art, including iconography. Moreover, the new version will better understand user prompts, accurately reflecting longer and more complex inputs. Matt Arcaro, IDC’s research director for computer vision and AI, praised Firefly Image 3 for its significant improvements in image quality and coherence with user prompts compared to its predecessor.
