Home
Adobe Project Indigo Unveils AI Photo Assistant to Boost Shooting and Editing with Large Models
Adobe is integrating a suite of AI-driven tools into Project Indigo, its experimental iOS camera application. Leveraging large language models (LLMs), the app analyzes image content to deliver photography critiques, editing recommendations, and intelligent optimization strategies. Building on previous support for professional shooting controls, multi-frame super-resolution, and diverse photography modes, this update significantly boosts AI-assisted creative workflows.
Key additions include photo critiques, shooting and editing suggestions, advanced object removal, AI-generated depth of field, and style transfer. The critique feature offers professional-grade analysis covering composition, lighting, color balance, and emotional impact. Meanwhile, shooting suggestions provide actionable advice on re-composing, exposure adjustments, and visual optimization to help users refine their photographic techniques.
Marc Levoy, Project Indigo’s lead developer and former Google Pixel camera technology contributor, noted that most generative AI image tools depend on user prompts—a process often challenging for casual users to execute accurately. Consequently, Project Indigo prioritizes button-driven, deterministic operations, enabling the AI to deliver direct, executable editing solutions.
Regarding smart editing, the new object removal tool automatically identifies and eliminates distracting background elements, such as pedestrians, trash bins, utility poles, and vehicles. It also allows users to specify objects for removal via text descriptions. This approach reduces manual effort and enhances processing outcomes compared to traditional selection methods.

Furthermore, the app uses AI to generate depth-of-field effects, simulating background blur for standard photos. It also offers style transfer effects, including watercolor, pen sketches, colored ink lines, monochrome, and backlighting. However, since style transfer is not a novel technology, its practical utility requires further validation.
Currently, Project Indigo’s new AI capabilities are powered by Google’s Nano Banana model, based on Gemini. Adobe indicated it may test other AI models in the future, including its proprietary Adobe Firefly model. These features are currently accessible via the "AI Playground" testing area for a limited group of users, with full public release yet to be determined.
Related article
Ando Launches Team Messaging App Bridging Human and AI Collaboration
In 2025, as Sara Du assisted companies in developing MCP servers, a recurring question emerged: how could teams leverage AI agents directly within Slack? The path was obstructed by significant technical barriers, including the complexity of message s
Sequoia-backed Empirik raises $21M to forecast outages before they strike
Before joining Sequoia Capital in 2020 as chief digital and information officer, Avon Puri spent over a decade running infrastructure at Rubrik and VMware. Three years ago, as large language models began showing their true potential, Puri, alongside
OpenAI launches GPT-5.5 Instant as ChatGPT’s new default model
OpenAI launched GPT-5.5 Instant on Monday, replacing GPT-5.3 Instant as the default ChatGPT model. The company states that this update minimizes hallucinations in high-stakes fields like law, medicine, and finance, while preserving the fast response
Related Special Topic Recommendations
Comments (0)
0/500
Adobe is integrating a suite of AI-driven tools into Project Indigo, its experimental iOS camera application. Leveraging large language models (LLMs), the app analyzes image content to deliver photography critiques, editing recommendations, and intelligent optimization strategies. Building on previous support for professional shooting controls, multi-frame super-resolution, and diverse photography modes, this update significantly boosts AI-assisted creative workflows.
Key additions include photo critiques, shooting and editing suggestions, advanced object removal, AI-generated depth of field, and style transfer. The critique feature offers professional-grade analysis covering composition, lighting, color balance, and emotional impact. Meanwhile, shooting suggestions provide actionable advice on re-composing, exposure adjustments, and visual optimization to help users refine their photographic techniques.
Marc Levoy, Project Indigo’s lead developer and former Google Pixel camera technology contributor, noted that most generative AI image tools depend on user prompts—a process often challenging for casual users to execute accurately. Consequently, Project Indigo prioritizes button-driven, deterministic operations, enabling the AI to deliver direct, executable editing solutions.
Regarding smart editing, the new object removal tool automatically identifies and eliminates distracting background elements, such as pedestrians, trash bins, utility poles, and vehicles. It also allows users to specify objects for removal via text descriptions. This approach reduces manual effort and enhances processing outcomes compared to traditional selection methods.

Furthermore, the app uses AI to generate depth-of-field effects, simulating background blur for standard photos. It also offers style transfer effects, including watercolor, pen sketches, colored ink lines, monochrome, and backlighting. However, since style transfer is not a novel technology, its practical utility requires further validation.
Currently, Project Indigo’s new AI capabilities are powered by Google’s Nano Banana model, based on Gemini. Adobe indicated it may test other AI models in the future, including its proprietary Adobe Firefly model. These features are currently accessible via the "AI Playground" testing area for a limited group of users, with full public release yet to be determined.
Ando Launches Team Messaging App Bridging Human and AI Collaboration
In 2025, as Sara Du assisted companies in developing MCP servers, a recurring question emerged: how could teams leverage AI agents directly within Slack? The path was obstructed by significant technical barriers, including the complexity of message s
Sequoia-backed Empirik raises $21M to forecast outages before they strike
Before joining Sequoia Capital in 2020 as chief digital and information officer, Avon Puri spent over a decade running infrastructure at Rubrik and VMware. Three years ago, as large language models began showing their true potential, Puri, alongside
OpenAI launches GPT-5.5 Instant as ChatGPT’s new default model
OpenAI launched GPT-5.5 Instant on Monday, replacing GPT-5.3 Instant as the default ChatGPT model. The company states that this update minimizes hallucinations in high-stakes fields like law, medicine, and finance, while preserving the fast response











