Google is expanding the capabilities of its AI assistant Gemini by building in a new image-annotation tool that brings editing and markup features directly into the app. Soon, users won’t have to export AI-generated or uploaded photos to a separate program just to make tweaks — they’ll be able to draw, highlight, or add text on images from within Gemini itself. Beyond simple markup, the tool aims to let users visually specify changes (for example, circling a background element and asking Gemini to replace or remove it), offering far greater control and convenience for edits and refinements.
This shift turns Gemini from a generation-only tool into a more complete creative workspace: you can generate a picture, annotate it, refine it, and iterate — all inside the same interface. For creators, designers, casual users and anyone who edits images occasionally, this removes the friction of jumping between apps while giving instant access to intuitive, integrated editing. In effect, Gemini becomes both a prompt-based generator and a lightweight editor.
Because this feature is being built into the web version first (with wider rollout planned), once available it could make AI-powered editing significantly more accessible to people who want quick adjustments — from background swaps to simple annotations, all without the learning curve of traditional photo-editing software.
For those who use Gemini often for visuals — whether for social media, concept work, or just personal projects — this update promises a smoother workflow. Rather than treating generated images as static outputs, Gemini will let you treat them as living drafts: tweak, annotate, refine, and finalize without leaving the app.
