Google has introduced AI-powered image editing capabilities in its Gemini platform. This enhancement allows users to apply text-based prompts directly within the Gemini app or website to modify existing images. Previously available in Google AI Studio, this feature is now being made accessible to all Gemini users, covering a total of 45 languages. The tool supports conversational prompts for editing both AI-generated visuals and personal images uploaded from devices.

Capabilities of Gemini’s AI Image Editing

The standout aspect of this innovation is its ability to democratize photo editing. Engaging with the Gemini AI chatbot enables users to either generate new images or upload personal photographs for enhancement requests. This process is reminiscent of the Reimagine feature in Google Pixel, which allows for the addition of virtual elements to real-life photos.

Gemini’s editing toolkit includes options to swap objects, modify backgrounds, or introduce completely new elements. As outlined in Google’s official blog announcement, users can upload a photo and request adjustments, such as changing hair color for a virtual makeover. The AI retains memory of past requests, facilitating multiple adjustments across various interactions. Furthermore, there’s potential to create stories accompanied by generated images.

However, the introduction of such features does raise certain ethical questions. Notably, the possibility of producing deceptive imagery that could inflict harm on individuals or businesses is a significant concern. In response, Google plans to implement an invisible watermark on all AI-generated images. The company is also testing a visible watermark to enhance the identification of images that have undergone AI edits.