Written by Stephen Nellis
(Reuters) – Adobe said on Tuesday it plans to bring full artificial intelligence image generation tools to its Photoshop software later this year.
Adobe's image and video editing tools are widely used by creative professionals, but are facing increased competition from startups such as Microsoft-backed OpenAI, Midjourney and Stability AI. All of these companies offer services that can generate images from text prompts.
Adobe is developing its own image-generating AI system, called Firefly, trained on Adobe-proprietary data to avoid copyright claims against users.
Adobe previously released an image generation tool in Photoshop that lets you fill in and extend parts of existing images. Full image generation based on a new AI system called Firefly Image 3 is expected later this year, the company said at a conference in London on Tuesday.
Adobe focuses on speeding up the work of professionals who use its software. The new image generation tool includes the ability to tap on a user-uploaded image and use it as a reference for the overall composition of the image.
For example, a designer can create a quick sketch of a scene on a napkin, take a photo of that napkin with a smartphone, and ask Photoshop to generate fully-featured images in different styles, and digitally said Eli Greenfield, Chief Technology Officer. Adobe media.
“Instead of having to make sure you're explaining exactly what's where and specifying what's needed and what's not, you're borrowing from a reference. So this is amazing. “It's a powerful feature,” Greenfield said. He said.
Adobe said a test “beta” version of the software would be available to some users on Tuesday, but did not provide a date for general availability.
(Reporting by Stephen Nellis in San Francisco; Editing by Jamie Freed)