Google is quietly expanding the capabilities of its Gemini AI platform with a suite of advanced image editing and analysis tools currently in testing
These new features enable users to interact more intuitively with uploaded images by marking up specific areas to guide the AI's focus and responses
Available to select users on both the Gemini mobile app and the web version in Chrome the tools appear after an image is added to a conversation
Tapping or clicking the photo reveals a visual overlay with options to draw freehand lines in various colors circle key elements or add explanatory text directly onto the image
This markup system works seamlessly across mobile and desktop environments offering the same robust set of annotation choices
The functionality builds on Gemini's existing strengths in image generation and understanding previously showcased through playful models like Nano Banana and the more sophisticated Nano Banana Pro powered by Gemini 3 Pro
By letting users highlight objects people or details the tools help refine AI interactions making edits more targeted and analyses more accurate
While Gemini's object and person recognition remains imperfect at times the manual markup significantly boosts precision allowing the AI to zero in on user-intended sections
Early reports indicate the feature is live in version 16.49.59 of the Google app and accessible even to free-tier users
Compared to streamlined options like Circle to Search this markup approach provides greater flexibility for complex modifications and in-depth reviews
As Google continues refining Gemini these annotation capabilities mark another step toward more collaborative and visually driven AI conversations blending creative control with intelligent automation