Adobe Brings Its Text-To-Image Art Generator ‘Firefly’ To Google’s Bard

Adobe has brought its text-to-image art generator, Firefly, to Google’s Bard. Announced today at Google’s I/O 2023 event, this advanced artificial intelligence system enables creators to design and produce various artistic content.

With the Firefly system, users can fashion images from simple text prompts written directly into Bard. However, not all AI-generated pictures come out perfectly. As such, Adobe has integrated its online photo editor, Adobe Express, into the new feature. This allows creators to adjust things like the exposure or color of Firefly-generated results easily. Users can also select templates, fonts, and stock images from the Express library within Bard.

One of the selling points of the Firefly system is its training on licensed content from Adobe Stock as well as openly-licensed and public domain assets, ensuring that the input data is copyright-safe. Additionally, Adobe promotes transparency with its users about the images used in its data. For example, the partnership employs the Content Authenticity Initiative’s (CAI) open-source Content Credentials attached to the produced photo. A digital “nutritional label” provides information about where the picture was generated from and remains with the final product, regardless of where it is published later.

Overall, Adobe’s Firefly text-to-image art generator could help creators who want to explore new avenues of artistic expression. “The incredible response to our Adobe Firefly beta demonstrates the power and potential of generative AI to inspire more people to create and the strong demand for a creator-centric, commercially viable approach,” says Ely Greenfield, CTO of Digital Media at Adobe. “We’re empowering millions more people to use Firefly for creative inspiration and design and share standout content with Adobe Express through this integration with Bard by Google.”

[via Adobe]