Adobe is adding new AI-powered features to its experimental iOS camera app Project Indigo was launched last year. The app previously offered professional controls, multi-frame super resolution and various shooting modes, and now adds features that will use LLMs (large language models) to critique photos and make editing suggestions.
It also adds other AI features like advanced object removal, depth of field creation and the ability to add different styles to photos.
Adobe project lead Marc Levoy previously developed the Pixel’s camera chops. He said most generative AI tools provide operational-based editing, and it can often be a difficult endeavor to fix a photo or find the perfect suggestion to get the right result. That’s why most of the new experimental AI features are buttons that can produce more deterministic results.
For example, Google Camera trainer feature for Pixel phoneslaunched last year, offering more general framework suggestions. Project Indigo’s features, by comparison, are fairly descriptive and may help you learn some photography tricks, even if you don’t agree with the AI’s assessment.
There are two features in this category. The first is a photo critique that includes “professional” feedback on framing, lighting, colors, and emotional impact.
The second is shooting and editing suggestions, which give tips on reshooting the photo, including how you can change the frame, exposure, and objects in the viewfinder. For example, the app told me to remove a hexagonal white object in a frame from a photo I took.
The second section tells you how you can use Adobe Lightroom controls to make an existing photo better.
Photography software, including Apple Photos, Google Photos, and Adobe Photoshop, have offered object removal for years. But the feature often depends on the user dragging around or selecting an object by drawing on the screen, which isn’t perfect every time.
Project Indigo’s new feature provides transitions for objects to be removed from the image, such as people in the background, trash and trash cans, wires and poles, fences, vehicles, and other clutter. You can also describe a specific object to delete. The results of this feature are quite impressive.
The app removed my friend and the object he was holding from the background without creating any weird artifacts.
The app also lets you use artificial intelligence to create depth of field for a photo to simulate a blurred background.
With this new update, Adobe is also testing a style transfer feature that lets you convert your image to tones like watercolor, pen and ink, ink line with color wash, monochrome and backlit theme. Some styles remind me Early days of Prisma implementation. With advanced models, the outputs look elegant, but the style transfer is not a new or useful feature.
Despite Levoy’s criticism of its operational implementation, Project Indigo has its own feature that allows you to describe your editing. Users can use it to perform editing flows that are not available in the predefined tools. But it’s also a potential path to the slopes.
The company uses Google’s Gemini-based Nano Banana for these features, but it is open to switching to other models, including its own Adobe Firefly model. These features, grouped under the AI playground banner, are still in testing and only select users will have access to them. These features may never reach a wider audience, but it’s good to see some features that can make people aware of the nuances in photography, instead of just creating more fluff.
When you purchase through links in our articles, we may earn a small commission. This does not affect our editorial independence.
