Adobe is adding new AI-based features to its experimental iOS camera app called Project Indigo, which launched last year. The app previously offered professional-level controls, multi-frame super-resolution, and a variety of capture modes, and now it’s adding the ability to critique photos and provide editing suggestions using Large Language Models (LLMs).
Other AI features have also been added, such as advanced object removal, depth of field creation, and the ability to add different styles to your photos.
Adobe project lead Marc Levoy had previously developed the Pixel’s camera chops. He said most generative AI tools offer prompt-based editing, and often retouching a photo or finding the perfect prompt to get the right result can be a tricky endeavor. That’s why most of the new experimental AI features are buttons that can produce more deterministic output.
For example, Google’s Camera Coach feature for Pixel phones that launched last year offered more general framing suggestions. By comparison, Project Indigo’s features are fairly descriptive and may help you learn a few photography tricks, even if you don’t agree with the AI’s assessment.
This category has two features: The first is a photo critique, which includes “professional” comments on framing, lighting, color, and emotional impact.
The second is Capture and Editing Suggestions, which gives tips for retaking photos on how to change framing, exposure, and objects in the viewfinder. For example, an app asked me to remove a white hexagonal object in the frame of a photo I had taken.
The second section explains how to use existing photos to create better photos using Adobe Lightroom controls.
Photos apps, including Apple Photos, Google Photos, and Adobe Photoshop, have offered object removal features for years. However, this feature is not perfect every time, as it often relies on the user drawing on the screen or selecting objects.
A new feature in Project Indigo provides a toggle for what to remove from the image, such as people in the background, trash cans, power lines and poles, fences, vehicles, and other clutter. You can also describe the custom object you want to remove. The results of this feature are very 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 simulate a blurry background by creating depth of field in your photos using AI.
With this new update, Adobe is also experimenting with a Style Transfer feature that lets you turn your photos into tones like watercolor, pen and ink, ink lines with color washes, and solid and backlit subjects. Some of the styling reminds me of the early days of the Prisma app. With higher-end models, the output looks stylish, but style transfer isn’t a new or useful feature.
Despite Levoy’s criticism of the prompt-based implementation, Project Indigo has its own ability to explain edits. Users can use it to perform editing flows that are not available in the preset tools. But this is also a potential road to slope.
The company is using Google’s Gemini-based Nano Banana for these features, but you can swap it out for other models, including its own Adobe Firefly model. These features bundled in the AI Playground tab are still in the testing phase and only accessible to selected users. These features may not be available to a wider audience, but it’s nice to see some features that help people recognize nuances in photos rather than just creating more errors.
If you purchase through links in our articles, we may receive a small commission. This does not affect our editorial independence.
