Google continues to improve Gemini, its artificial intelligence application, and is preparing new functions that will allow users More accurately mark and describe edits to images.
This update significantly expands the experience compared to the basic tools that the company had previously offered.
Until recently, Gemini’s markup system only allowed you to highlight areas of the image or add simple text, while any more complex adjustments required manually explaining the desired change to the AI. This approach limited speed and accuracy, especially for Gemini-generated images such as those from Nano Banana.
The latest advances show that Google is preparing a much more complete dialing interface. In the latest beta version of the Android app, tapping the pencil icon takes users to a rich editing panel. In addition to the basic tools, Resizing options, effects and a text box are incorporated that allow you to clearly describe the desired changes.
Advanced markup promises to be especially useful for complex images, where small details can significantly affect the final appearance. With these new features, Users will be able to point to specific areas, adjust their size, apply preliminary effects and provide precise instructions to Geminiall within the same interface.
Although some of these features are not yet fully implemented in the beta version, the update represents a clear step towards more granular control over editing AI-generated images. Users will be able to apply precise adjustments without leaving the Gemini interface, increasing efficiency and creativity.
With these improvements, Gemini could establish itself as a competitive tool for AI-assisted image editing, offering not only content generation but also detailed control over the results.