Photo credit: www.androidcentral.com
What You Need to Know
An analysis of an APK indicates that Google may soon allow users to upload up to ten images at once to its Gemini AI. Currently, the system only permits the upload of a single image, with any subsequent uploads replacing the previously submitted one. This new functionality was observed in the beta version of the Google app, specifically v16.11.32.
Google has been steadily enhancing the capabilities of Gemini, introducing features such as Gems, Gemini Live, and screen recording, even for its free-tier users. However, a fundamental limitation persists with regard to multiple image uploads—a restriction that appears to be on the verge of change.
An APK teardown conducted by Android Authority through Assemble Debug has uncovered a concealed feature enabling the upload of up to ten images simultaneously.
Under the current system, users are restricted to one image per prompt. If they attempt to upload more, Gemini prompts them to either replace the existing image or proceed with just one. This limitation complicates users’ ability to secure comprehensive analyses of multiple images in a single interaction.
The publication reported that with the Google app v16.11.32 beta, they successfully activated the capability to submit multiple images for review in the Gemini application. The assumption is that this function has been tested and is operational, but remains hidden until a wider release in a future update.
After enabling this feature during the teardown process, users could submit up to 10 images in one prompt for Gemini to analyze all at once, providing detailed descriptions of each image’s content. This addition is poised to significantly streamline the user experience, eliminating the need to upload each image sequentially for analysis, as demonstrated in the visual evidence provided.
While the timeline for broader availability of this feature remains unclear, its functional nature suggests that a rollout could be imminent.
Additionally, Google is set to launch its latest AI model, Gemini 2.5 Pro, to its Gemini Advanced subscribers today. The company emphasizes that it is integrating cognitive abilities into all versions of its Gemini 2.5 models, aiming to enhance complex problem-solving skills and establish context-aware AI agents.
Source
www.androidcentral.com