gen‑ai.news
← Back
Image

Adobe Lightroom mobile can now open closed eyes in photos with a simple tap

Adobe Lightroom mobile can now open closed eyes in photos with a simple tap

Adobe has rolled out a new generative AI feature to the mobile version of Lightroom on iOS, iPadOS, and Android that addresses one of the most common frustrations in portrait photography - subjects blinking at the wrong moment. When the app identifies that a person, or multiple people, have their eyes closed in a frame, it automatically surfaces an Open Eyes Quick Action as an icon overlaid on the image, keeping the workflow as frictionless as possible.

The ability to correct closed eyes is not entirely new territory for Adobe. Photoshop Elements has offered a similar tool for close to a decade, but the underlying approach there is meaningfully different. That older implementation works by sourcing replacement eyes from a separate photo of the same subject, which requires the user to supply additional reference material. The Lightroom mobile version, by contrast, uses generative AI to synthesize open eyes directly, meaning no second image is needed.

This distinction matters in practice. Many users will want to fix a blink in a one-of-a-kind shot - a group photo, a candid moment - where no convenient reference image exists. A generative approach sidesteps that limitation entirely, though it also raises the usual questions around accuracy and realism that come with any AI-synthesized content. The quality of the result will depend on how well the model handles varied lighting conditions, angles, and eye shapes across different subjects.

The feature sits within Adobe's broader push to bring Quick Actions - small, task-specific AI tools - to its mobile Lightroom apps. For photographers who do a significant portion of their editing on a phone or tablet, additions like this narrow the gap between mobile and desktop capabilities without requiring a complex editing workflow. The Open Eyes tool is available now in the Lightroom mobile app across all three supported platforms.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

Food Delivery App Apologizes for AI-Generated Menu Photos Showing Bacon Floating in Soda
Image

Food Delivery App Apologizes for AI-Generated Menu Photos Showing Bacon Floating in Soda

Food delivery platform Just Eat has issued an apology after AI-generated menu images appeared on its app showing clearly inaccurate food pairings - including bacon and eggs suspended in a fizzy drink. The incident has drawn attention to the risks of deploying generative image tools in contexts where visual accuracy directly affects consumer trust. Just Eat has not yet detailed the specific process that allowed the images to go live.

Google Opens SynthID AI Detection to the Public
Image

Google Opens SynthID AI Detection to the Public

Google has launched a public-facing website for SynthID, its AI watermarking and detection tool, allowing anyone to check whether an image has been created or significantly altered by AI. The tool works by reading watermarks embedded by Google's own image generation systems, which limits its coverage but makes it a practical first check for content from those pipelines.

AI-Edited Photos Can Lead People to Form False Memories
Image

AI-Edited Photos Can Lead People to Form False Memories

New research finds that AI-edited photos and videos can cause people to form false memories of events - and that exposure to manipulated imagery tends to make viewers more confident in those incorrect recollections. The findings raise fresh concerns about the psychological impact of AI-generated and AI-altered visual media as it becomes increasingly difficult to distinguish from authentic footage.