• Adobe, computer software said on Tuesday it plans to place a tool for full artificial intelligence image generation in its Photoshop software later this year.
  • The company said full image generation will come later this year, based on a new AI system called Firefly Image 3.
  • Adobe said a test “beta” version of the software is available to some users on Tuesday but did not give a date for general availability.

The computer software company Adobe announced on Tuesday that later this year, a feature for fully artificial intelligence image generation will be added to its Photoshop program. The new image-generation tool will have the ability to tap a user’s uploaded image as a reference for the general composition of an image.

Tool for full artificial intelligence image generation

Adobe is developing its image-generation AI system called Firefly. This is done to protect itself from user-filed copyright infringement lawsuits.

Photoshop image-generation tools, previously released by Adobe, can enlarge or fill in specific areas of an existing image. The company announced at a conference on Tuesday in London that full image generation, based on a new AI system called Firefly Image 3, will arrive later this year.

Adobe has prioritized expediting the work of professionals utilizing its software. A user’s uploaded image can be used as a model for the overall composition of an image by the new image-generation tool.

For instance, according to Ely Greenfield, chief technology officer for digital media at Adobe, a designer could quickly sketch out a scene on a napkin, take a picture of it with a smartphone, and then instruct Photoshop to produce fully featured images in a range of styles.

“It’s borrowing from the reference rather than having to very carefully describe exactly what goes where and try to make sure that I’m specifying the things I want and that I don’t.” Thus, this is a very potent capability, according to Greenfield.

Also read: Generative AI in the pharmaceutical industry

Also read: Adobe Premiere Pro’s generative AI tools make video editing easier

More information

Adobe did not provide a date for the software’s general release, but it did say that a test version, or “beta,” would be accessible to some users on Tuesday.

Creative professionals use Adobe’s image and video editing tools extensively, but OpenAI, Stability AI, and Midjourney—three startups backed by Microsoft—all offer services that can create images from text prompts, and they are becoming more and more competitive, according to Reuters.