Adobe is adding new AI-powered features to its experimental iOS camera app released last year called Project Indigo. The app previously offered pro controls, multi-frame super resolution, and various capture modes, but now it has added the ability to critique photos and provide editing suggestions using LLM (Large-Scale Language Model).
We’ve also added other AI features, including advanced object removal, depth of field generation, and the ability to add different styles to your photos.
Marc Levoy, who leads the project at Adobe, previously developed the Pixel’s camera chops. He said most generative AI tools offer prompt-based editing, and often finding the best prompts to tweak a photo or get the right results can be a difficult task. That’s why most new experimental AI features are buttons that can produce more definitive output.
For example, Google’s Camera Coach feature for Pixel smartphones released last year offered more general framing suggestions. In comparison, Project Indigo’s features are fairly descriptive and can help you learn the tricks of photography even if you don’t agree with the AI’s assessment.
This category has two functions. The first is photo criticism. This includes “expert” opinions on framing, lighting, color, and emotional impact.
The second is Capture and Edit Suggestions, which provide tips on retaking photos, such as how to change framing, exposure, and objects in the viewfinder. For example, the app told me to remove a hexagonal white object in the frame from a photo I took.
The second section explains how to use Adobe Lightroom controls to further improve your existing photos.
Photo apps like Apple Photos, Google Photos, and Adobe Photoshop have offered object deletion for years. However, this functionality often relies on the user rotating and selecting objects on the screen, and is not always perfect.
A new feature in Project Indigo lets you toggle what to remove from your images, including people in the background, trash and trash cans, power lines and poles, fences, vehicles, and other clutter. You can also write custom objects to delete. The results of this feature are very impressive.
The app removed my friend and the object he was holding from the background without producing any strange artifacts.
The app also uses AI to create depth of field in your photos and simulate blurry backgrounds.
With this new update, Adobe is also experimenting with the style transfer feature. This allows you to turn your photos into tones such as watercolor, pen and ink, color washed ink lines, black and white, backlit subjects, and more. Some of the styles remind me of the early days of Prisma apps. For advanced models, the output may look sophisticated, but style transfer is neither a new nor a useful feature.
Despite Levoy’s criticism of prompt-based implementations, Project Indigo has the unique ability to explain edits. Users can use it to perform editing flows that are not available with preset tools. However, this is also a potential road to slope land.
The company uses Google’s Gemini-based Nano Banana for these features, but is open to swapping it out for other models, including its own Adobe Firefly model. These features bundled with the (AI Playground) tab are still in the testing phase and are only accessible to selected users. These features may never reach a wider audience, but it’s good to see some features that can make people appreciate the nuances of photography instead of just creating something vulgar.
If you buy through links in our articles, we may earn a small commission. This does not affect editorial independence.
