Gemini Has Added New AI-Powered Image Editing Tools.
One way to rapidly improve AI models is by enhancing their image editing capabilities, allowing them to quickly handle tasks that previously required significant time and effort in Photoshop. This is undoubtedly one of the main reasons Adobe decided to release its own ChatGPT plugins .
Want your T-shirt to be blue instead of red? Need to crop out a person or object from a perfect group selfie? Now AI-powered chatbots can easily and professionally perform these tasks with just a text message. No digital photo editing skills required; just describe what you want to achieve.
Over the past few months, Gemini and ChatGPT have significantly improved editing precision. They can now adjust only part of an image while leaving the rest untouched, rather than having to redraw the entire image from scratch just to change one detail. Now, Gemini has quietly added several more markup tools for this task.
Image Markup in Gemini
Google hasn’t officially announced these markup tools, suggesting the feature is still in testing (it was also previously spotted by the Android Authority team). If you don’t see these tools, try closing and restarting the Gemini app on your mobile device or refreshing the app page on the web. If you still don’t see the desired options, you may need to wait a bit longer.
If this feature is already available, you can upload an image to the chat by using the “+” button in the request window, then tap or click on the image thumbnail to access the markup tools. Currently, these tools are only visible before you begin editing the image; once you’ve started editing, they’re unavailable.
The easiest tool to use is the drawing tool, which is activated by a doodle-like icon. With it, you can highlight a specific part of an image—an area in the sky, a lamppost on the street, a face in a crowd—and then describe the change you want Gemini to make.
For example, instead of simply writing “add a cartoon dragon to the sky” in a task, you could combine that task with a circle on the image that precisely indicates where the dragon should be. This will give you even greater precision, comparable to Photoshop, without overwhelming the interface.
Drawings can also be used when asking questions about an image. For example, you can circle an actor or object in the image and then ask “Who is this?” or “What is this?” in the attached query. In this sense, it works similar to the “Circle to Search” feature available for images on Android.
There’s also a text tool—the T icon—but I’m not exactly sure how to use it (and there’s no official help yet). It lets you describe the changes you want to make to the image (for example, “add an arrow here”), but the text stays in place—it’s almost like a primitive text overlay feature, with color selection but no font or style options.
This tooltip lets you edit the added text, for example, by adding outlines and backgrounds, so perhaps that’s what it’s intended for: a more precise text editing tool. Presumably, once these tools are available to all Gemini users, we’ll receive more information from Google about how to use them—but it’s quite possible they’re already available to you.