Follow ZDNET: Add us as a favorite source On Google.
ZDNET Highlights
- Adobe has launched new AI image-generating tools in Adobe Max.
- The Adobe Firefly Image Model 5 is the company’s most capable model.
- The editing prompt feature lets you edit images using natural language.
The launch of OpenAI’s DALL-E 2 in 2022 ignited the AI text-to-image generator craze, with dozens of tools launching over the past few years. Still, the use cases for these image generators are quite limited, and they lack everyday, realistic applications for the average person. Adobe’s latest image model wants to change that problem.
Also: The most popular AI image and video generator may surprise you – here’s why people use it
At its annual Adobe Max creativity conference, the company unveiled its new Adobe Firefly Image Model 5, which the company describes as its most advanced image creation and editing model to date. Apart from creating high-quality images, the model can also help you edit your existing photos using AI. After seeing demos of the editing features, I think the model solves an important problem for users.
Adobe Firefly Image Model 5
The new model can now produce images in native 4MP resolution, which contains more context and has almost twice the pixels as 1080p, resulting in better detail. Adobe claims the results are high quality images with “photorealistic” results.
Also: Why open source can’t survive the rise of generic AI
Adobe says this attention to detail means the model can tackle challenging tasks, such as physically accurate images, natural motion, and multi-layered compositions. The real magic of this approach comes to life in the new photo-editing features.
Photo editing made easy
Sometimes you’ll take a shot that has potential but needs a few tweaks to make it perfect. Whether changes are simple or complex, they often require you to become familiar with editing software and click the right buttons to make adjustments, making the process more complex and time-consuming. With Adobe’s new tool, you can ask AI to do the editing, and the job will be done.
As the name suggests, the new Prompt to Edit tool, powered by Firefly Image Model 5, lets you use an interactive prompt to take actions on your photo. I got to see a live demo of the feature before release and I was blown away.
In the demo, the person uploaded a photo of his dog sitting behind a fence. Then he asked the tool to remove the fence from the photo. In a matter of seconds, the fence was removed from the dog photo, with AI filling in the areas where the object previously stood to create a realistic-looking image. Google launched a similar feature called Edit with Ask Photos earlier this year with the launch of the Google Pixel 10, and I found that tool just as useful.
Also: Is it risky to use Sora 2 and other AI video tools? This is what a legal scholar says
Building off this feature is layered image editing, which maintains the compositional accuracy of the image while making adjustments to elements of the image. For example, in sizzle videos, multiple items are displayed on a surface, but the user can then select one, drag and drop it, resize it, and even make changes to it with a gesture. This task is usually a very complex process in Photoshop that requires many tools, steps, and precision.
how to reach
The Prompt to Edit feature is now available to Firefly customers, supporting the Firefly Image Model 5 and partner models from Black Forest Labs, Google, and OpenAI. Firefly Image Model 5 is available in beta today. Finally, while shown on Adobe Max, the layered image editing feature is still in development.
