Google is reportedly working on improving the image generation capabilities of the Gemini chatbot. The Mountain View-based tech giant is adding a built-in image editing feature to an artificial intelligence (AI) bot, according to a new report. The feature was spotted in the latest beta version of Google’s app, and while it’s reportedly being developed for smartphones, it’s unclear if it will be available on the web client. In fact, the Microsoft Designer platform already offers a built-in editing feature powered by Copilot.

Gemini Inline image editing

According to a report by Android Authority, the new feature has been spotted in the Google beta app for Android 15.40.31.29. The publication saw it during the unpacking process of an Android application (APK). Those who signed up for Google’s beta program won’t be able to test it because it’s not a visible feature.

Until now, image editing using Gemini has been a difficult task. This is because if the user doesn’t like a certain detail in the image, they will have to add more details in a subsequent query to generate a new iteration. However, the next iteration might remove good parts of the previous image and introduce new aberrations. There was no way to keep the good parts while eliminating the not-so-good parts.

But that could change with the new feature. Based on a demonstration video shared by the publication, the feature works based on a combination of two user interactions. Once the image is generated, the user can highlight a part of the image and add a tracking query, and Gemini will change only that part of the image, leaving the rest untouched.

However, as users can see in the video demo, the feature is far from finished. In several cases, he still changed the entire image despite being instructed to change only part of it. But it’s possible that these issues will be resolved when the feature is rolled out to users.