What you need to know
- An APK teardown reveals that Google could be working on letting you upload up to ten images onto Gemini.
- As of now, users can only upload one image and additional images get replaced with the one that has been uploaded onto the chatbot.
- This feature showed up on the beta version of the Google app v16.11.32.
Google has been making several improvements to Gemini's capabilities, bringing more features like Gems, Gemini Live and screen recording to the free tier. However, the most basic ability to upload multiple images on to the AI chatbot seems to be missing—but this could change soon.
An APK teardown performed by folks at Android Authority via Assemble Debug seems to have revealed a hidden feature that allows users to upload multiple images with a limit of 10 pictures at once.
Currently, users can upload only one image per prompt. If they try to upload more images, Gemini will ask if they'd like to replace the already uploaded file with a new one. This limits the user's need to give Gemini more information to get an all-around analysis of several images in one go.
The publication added that, with the Google app v16.11.32 beta, they were able to activate the ability to upload multiple images for analysis in the Gemini app. They assume that this feature was already tested and made functional for users but has been hidden for the masses to be released through an update in the future.
Once this feature was enabled during the teardown, they were able to attach up to 10 images onto Gemini's app within a single prompt, and Gemini was able to analyze all the images in one go, describing what those images contained. This feature would significantly reduce the time it takes for users to upload one image in each prompt and then wait to upload the next for the chatbot to interpret, as seen in the screenshot above.
While we don't know if and when this feature will roll out to users on a larger scale. However, since it seems pretty functional, this rollout could happen in the near future.
Furthermore, Google has just released its most advanced AI model — Gemini 2.5 Pro, starting today to its Gemini Advanced subscribers. The company says it is building thinking capabilities into all its Gemini 2.5 models, moving to enable complex problem-solving abilities and serve as context-aware AI agents
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.
