US tech giant Google has launched a major update to its Gemini AI image generator, launching an innovative editing tool that allows users to fine-tune specific parts of the generated image. The feature, now included in the latest Android 15 beta, aims to provide a more customizable approach to image generation by enabling users to precisely edit certain parts of an image. However, while the tool offers exciting new possibilities, its current state of testing suggests it may not be perfect yet.
According to Android Authority, Google is enhancing its AI image generation capabilities by allowing users to interact more directly with content. Previously, users could only generate images through text prompts. Newly added functionality builds on this foundation, enabling users to highlight areas of images and request changes.
For example, during the demo, the user generated an image of a dog wearing a hat and sunglasses and then asked to “change the hat to a birthday hat.” Artificial intelligence quickly adjusts the image to reflect the request.
The tool’s most significant advancement is its ability to allow users to pinpoint specific parts of an image for modification. This provides finer control over the final result, making it possible to customize the output in previously difficult ways. Despite the improvements, the feature is not without limitations.
Additionally, the demo footage showed that the AI ​​sometimes struggled to accurately understand requests, with some edits showing inconsistencies. The process of making the changes also took considerable time, and the tool is expected to be further refined before its official release.
Google’s move is part of its ongoing efforts to improve its Gemini AI image generator, which has been in development since the platform’s launch. The feature is still in beta, and Google says users can expect speed and accuracy improvements as the feature matures into a full version.