Google Gemini might soon allow more extensive editing of AI-generated images

Google’s Gemini AI chatbot is set to receive a major update that will allow users to easily refine and customize AI-generated images. This new feature, found in the code of the latest Google beta app for Android (v15.29.34.29 beta), promises to be a game-changer for those frustrated by Gemini’s current lack of editing options.

At present, Gemini only supports creating images from text prompts and lacks functionality for modifying generated images. Users who want to change specific details have to generate a new image with a revised prompt, which can be time-consuming.

The upcoming update aims to address this issue by introducing two new methods for fine-tuning AI-generated images. The first method will allow Gemini to interpret natural language prompts for image modifications. For example, if you’re satisfied with the image overall but wish to alter the background, you can simply instruct Gemini to make that change without having to create a completely new image.

The second method is even more user-friendly. You’ll be able to use your finger or a stylus to circle the area of the image you want to alter and then specify the desired changes. This approach removes the need to describe the exact part you wish to edit, as Gemini will automatically recognize the circled area.

Although this feature is still in development and not fully operational yet, it represents a significant enhancement to Gemini’s capabilities. It indicates Google’s commitment to improving the user experience by offering more control and flexibility in image editing.

This update is likely to be especially valuable for creative professionals and anyone who regularly uses AI-generated images, such as for YouTube thumbnails or blog headers. It will simplify the editing process and allow for more personalized adjustments, ultimately saving users time and effort.