A new feature in Adobe’s camera app will critique your photos using AI

Adobe is adding new AI-powered features to its experimental iOS camera app called Project Indigo, which launched last year. The application previously provided professional controls, high-resolution multi-frames, and different shooting modes, and now we are adding features that will use LLMs (large-scale language models) to critique images and provide editing suggestions.

It also adds some AI features, such as advanced object removal, depth of field rendering, and the ability to add different styles to images.

Marc Levoy, the person in charge of Adobe’s project, had previously developed the chops for the Pixel’s camera. He said that most of the AI ​​production tools offer fast-based editing and, often, finding the perfect information to adjust an image or get the right result can be a tricky endeavor. That’s why many new AI test features are buttons that can produce more decisive results.

For example, Google’s camera trainer feature for Pixel phones, introduced last year, offered general frame suggestions. Project Indigo’s features, by comparison, are pretty self-explanatory and can help you learn the tricks of photography, even if you disagree with the AI ​​test.

There are two aspects to this section. The first is photo criticism, which includes “expert” opinion about framing, lighting, colors, and emotional impact.

The second is shooting and editing suggestions, which give you tips on reshooting a photo by changing the frame, exposure, and things in the viewfinder. For example, the app told me to remove a white hexagonal object from the frame of a photo I took.

The second section tells you how to use an existing image to enhance it using Adobe Lightroom controls.

Photography applications, including Apple Photos, Google Photos, and Adobe Photoshop, have offered object removal for years. But the feature often depends on the user’s rotation or selecting an object by drawing on the screen, which is not always correct.

The new Project Indigo feature gives you edits for things to take out of the picture, such as people in the background, garbage cans and garbage cans, wires and poles, fences, cars, and other stuff. You can also define a custom item to remove. The results of this feature are amazing.

The app removed my friend and the object he was holding behind without creating any weird artifacts.

The app also lets you use AI to create depth of field for an image to simulate a blurred background.

With this new update, Adobe is also experimenting with the transfer style feature, which allows you to transform your image into tones such as watercolor, pen and ink, ink line with color wash, monochromatic, and backlit title. Some styles remind me of the early days of the Prisma app. With advanced models, the output looks refined, but the transmission of the style is not a new or useful feature.

Despite Levoy’s criticism of the fast-based implementation, Project Indigo has its own feature that allows you to define your programming. Users can use it to perform flow editing that is not available in pre-set tools. But this is also a potentially slopland road.

The company uses Google’s Gemini-based Nano Banana for these features, but is open to switching to other models, including its Adobe Firefly model. These features, grouped under the AI ​​Playground tab, are in the testing phase, and only selected users will get access to them. These features may not make it to a wide audience, but it’s nice to see some features that can make people aware of nuances in photos, rather than just creating more recoil.