You may soon be able to perform inline edits on Gemini-generated images

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

Gemini Inline image editing

According to an Android authority reportthe new feature was spotted in the Google for Android beta app version 15.40.31.29. It was spotted by the publication during the disassembly process of an Android application package (APK). Those who have signed up for the Google beta program cannot test it because it is not a visible feature.

Until now, editing an image with Gemini has been a tough task. This is because if a user doesn’t like a particular detail of the image, he or she must add more details in a follow-up prompt to generate a new iteration. However, the next iteration could remove the good parts from the previous image and also introduce new aberrations. There was no way to keep the good parts while eliminating the not-so-good ones.

But this may change with the new feature. Based on a demonstration video shared by the publication, the feature works based on a combination of two interactions by the user. Once an image is generated, the user can highlight part of the image and add a follow-up prompt, and Gemini will change only that portion of the image and leave the rest untouched.

However, as users can see in the video demo, the feature is far from complete. In several cases, the program changed the entire image despite the instruction to change only part of it. But it’s possible that these issues could be resolved when the feature rolls out to users.