Adobe is introducing new AI-powered features to its experimental iOS camera app, Project Indigo, which was launched last year. The app, which already offered pro controls and multi-frame super-resolution, now includes tools that use large language models to critique photos and provide editing suggestions. These features aim to make photography more accessible and improve the user experience. According to Marc Levoy, the person leading Adobe’s project, many generative AI tools rely on prompt-based editing, which can be challenging for users to master. That’s why Project Indigo’s AI features are designed to generate more deterministic outputs, offering clear and descriptive guidance to users.
The app now includes two main AI features: photo critique and capture and edit suggestions. The photo critique provides a 'professional' opinion on framing, lighting, colors, and emotional impact, while the capture and edit suggestions offer tips on reshooting a photo by adjusting framing, exposure, and objects in the viewfinder. For example, the app suggested removing a hexagonal white object from a photo. A second section allows users to enhance existing photos using Adobe Lightroom controls. Additionally, the app enables advanced object removal, such as people in the background, trash, wires, and vehicles, with impressive results.
Photography apps like Apple Photos and Google Photos have offered object removal for years, but Project Indigo’s approach is more automated and user-friendly. The app also includes a style transfer feature that transforms photos into various artistic styles, such as watercolor and pen and ink. Adobe is using Google’s Gemini-based Nano Banana for these features, though it is open to using other models, including its own Adobe Firefly model. These features are still in testing and are only available to select users.
Source: techcrunch
