2 Sources
2 Sources
[1]
Google Gemini could be about to take this idea right out of Circle to Search's playbook
It also supports Nano Banana highlights, letting you work on just one section of a picture. Give Gemini an image, and it's already quite good at figuring out what it's looking at. But what if you don't want it looking at everything in the image, or at least not looking at it all equally? If you can imagine how it might be useful to direct Gemini's attention to one particular part of a picture, we've got just the tool for you, as we spot Google's work to add markup tools to Gemini image input. As you're probably well aware, it's quite easy to upload an image to Gemini and ask questions about it. But looking through the changes in version 16.42.61.sa.arm64 of the Google app, we've been able to identify a slight tweak to that workflow that would let you draw on an image after selecting it from your gallery or shooting a new photo with your camera. Right now, this feels like a bit of a generic interface rather than one intentionally for communicating with Gemini. For instance, it's not yet clear why we have the ability to choose different colors here. Once you do highlight a portion of your image, you can start using that for your Gemini queries: Even without more explicit directions, Google's AI is smart enough to know that the part with the circle around it is something you're trying to draw attention to. But you're also free to directly tell it to perform an operation based on a highlighted region, as you can see in this example: Here we're tapping into Nano Banana's image editing capabilities and using this input flow to quickly remove unwanted content from a screenshot. As you can see, this has the potential to be a pretty useful addition to Gemini's toolset. We wouldn't be surprised if Google further modifies how you access it and mark your images up in the first place, but hopefully we're able to see something like this go live in the not-distant future.
[2]
Gemini May Soon Let You Highlight Parts of Images Using Markup Tools
This functionality could work like Google's Circle to Search feature Google appears to be working on improvements to Gemini's image input feature, and it could soon let users draw directly on uploaded or captured images. References to a new feature were reportedly spotted on an unreleased version of the Google app during an APK teardown. When the feature is released, users will be able to highlight specific parts of an image, and Gemini will then use those markings to offer better responses to their queries. This feature is also said to support Google's Nano Banana tool for image editing. Google's Image Markup Tools Let Gemini Focus on Important Sections An APK teardown of Google app version 16.42.61.sa.arm64 by Android Authority reveals that Google is developing image markup tools for Gemini. These tools will reportedly let users draw on images, either selected from the gallery or taken with the camera, before uploading them to Gemini. Once users highlight a specific part of the image using the markup tools, they can use that selection as the focus of their Gemini queries. This feature could help in getting more relevant responses. Photo Credit: Android Authority The publication has shared screenshots detailing the feature. Even without detailed instructions, Google's AI would be able to understand that the circled portion is an area of interest. Users can also give specific commands related to the highlighted section. The feature also reportedly supports Nano Banana's image editing tools, allowing users to erase unwanted elements from a screenshot. It's important to note that features spotted in development don't always end up in stable releases, and the markup tools for Gemini are likely to be available to beta testers before everyone else gets access to the feature. In recent weeks, several under-development features for Gemini have surfaced on the Web. A recent APK teardown of another version of the Google app revealed that a future update may allow users to issue longer voice commands without using Gemini Live. This might allow users to long-press the mic icon in Gemini's input box to issue longer commands. The teardown also suggested additional UI changes coming to the Gemini interface. Also, Google has expanded the Summarise Pages option to both the stable and beta versions of Chrome for Android earlier this month.
Share
Share
Copy Link
Google is developing new markup tools for Gemini that will allow users to highlight specific parts of images, enhancing the AI's ability to focus on particular areas for analysis and editing.

Google is set to enhance its AI assistant, Gemini, with innovative image markup tools, allowing users to interact more precisely with visual content. This development, discovered in version 16.42.61.sa.arm64 of the Google app, promises to revolutionize how users engage with AI for image analysis and editing
1
.The new feature will enable users to draw directly on images uploaded from their gallery or captured with their camera. By highlighting particular sections of an image, users can direct Gemini's attention to specific areas of interest. This functionality is reminiscent of Google's Circle to Search feature, suggesting a cohesive approach to visual interaction across Google's products
2
.Google's AI is designed to recognize highlighted areas as points of focus, even without explicit instructions. Users can also provide specific commands related to the marked sections, allowing for more targeted and relevant AI responses. This feature has the potential to significantly improve the accuracy and usefulness of Gemini's image analysis capabilities
1
.The markup tools will also integrate with Google's Nano Banana image editing capabilities. This integration allows users to quickly remove unwanted content from screenshots or perform other editing tasks directly within the Gemini interface. The combination of AI-powered analysis and editing tools could streamline various image-related workflows
1
2
.Related Stories
While the current interface for the markup tools appears somewhat generic, it's likely that Google will refine the user experience before public release. The ability to choose different colors for markups suggests that additional functionality may be in development. As with many features discovered in APK teardowns, the final implementation may evolve before reaching users
1
.It's important to note that features identified in development don't always make it to stable releases. The markup tools for Gemini are likely to be tested with beta users before a wider rollout. Additionally, Google is working on other Gemini enhancements, such as the ability to issue longer voice commands without using Gemini Live, and various UI improvements to the Gemini interface
2
.As Google continues to innovate in the AI space, these new image markup tools for Gemini represent a significant step forward in making AI interactions more intuitive and powerful for users dealing with visual content.
Summarized by
Navi
[1]
[2]