Google has unveiled new native image editing features in its Gemini chatbot, allowing users to modify both AI-generated and uploaded images directly within the app. This update enables real-time, conversational edits, such as adding objects, changing backgrounds, or refining details, all through natural language commands.
Powered by Google’s Gemini 2.0 Flash AI model, the new functionality is being gradually rolled out, with support for over 45 languages expected in the coming weeks. Initially launched in Google AI Studio in March, this feature has now been expanded to the Gemini app, a move that reflects positive user feedback and demonstrates Google’s commitment to enhancing AI-driven creative tools.
Also Read: Apple Launches ‘Snapshot’ Website to Centralise Celebrity Content
Users can either upload images from their devices or generate new ones using Gemini’s text-to-image capabilities, powered by Imagen 3. The integration of these tools offers a seamless editing experience, where users can refine images iteratively through a conversational interface.
This update solidifies Gemini’s position as a competitive player in the AI chatbot space, providing advanced image editing capabilities that rival other platforms.
