Adobe is adding new AI-powered features to its experimental iOS camera app called Project Indigo, released last year. The app previously offered professional controls, multi-frame super-resolution, and different shooting modes, and is now adding features that will use LLM (Large Language Models) to critique photos and provide editing suggestions.

It also adds other AI features, such as advanced object removal, depth of field generation, and the ability to add different styles to photos.

Marc Levoy, the person leading the project at Adobe, had previously developed the Pixel’s camera features. He said most generative AI tools provide message-based editing, and often finding the perfect message to modify a photo or getting the right result can be a tricky task. That’s why most new experimental AI features are push buttons that can generate more deterministic results.

For example, Google’s camera trainer feature for Pixel phones, launched last year, offered more generic framing suggestions. Project Indigo’s features, by comparison, are quite descriptive and could help you learn some photography tricks, even if you don’t agree with the AI’s assessment.

There are two characteristics in this category. First is photographic criticism, which includes a “professional” opinion on framing, lighting, colors and emotional impact.

The second is shooting and editing tips, which give you tips on how to retake the photo and how to change the framing, exposure, and objects in the viewfinder. For example, the app told me to remove the white hexagonal object from the frame of a photo I took.

A second section explains how you can use an existing photo to enhance it using Adobe Lightroom controls.

Photography apps, including Apple Photos, Google Photos, and Adobe Photoshop, have offered object removal for years. But the feature often relies on the user to circle or select an object by drawing on the screen, which isn’t always perfect.

Project Indigo’s new feature lets you toggle elements to remove from an image, such as people in the background, trash and trash cans, wires and poles, fences, vehicles, and other clutter. You can also describe a custom 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 strange artifacts.

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

With this new update, Adobe is also experimenting with the style transfer feature, which allows you to convert your image to tones such as watercolor, pen and ink, color wash ink line, monochrome, and backlit subject. Some styles remind me of the early days of the Prisma app. With advanced models, the results appear refined, but style transfer is neither a new nor useful feature.

Despite Levoy’s criticism of the prompt-based 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 pre-built tools. But this is also a potential path into neglected terrain.

The company is using Google’s Gemini-based Nano Banana for these functions, but is open to switching to other models, including its own Adobe Firefly model. These features, included in the AI ​​Playground tab, are still in a testing phase and only selected users will have access to them. These features may never reach a wider audience, but it’s nice to see some features that can make people aware of the nuances of photography, rather than just creating more garbage.