Summary

As good as Gemini is—it’s personally my main AI chatbot, after all—it still has some limitations that keep it from reaching its full potential. Among them, the fact that it limits you to uploading one single image at a time. Now, this is finally getting addressed.

Gemininow officially allows you to upload up to ten images simultaneously within a single prompt, a substantial increase from the previous limitation of just one image. Previously, attempting to add a second image to a prompt in Gemini would trigger a warning, asking if you wanted to replace the existing image. This restriction often forced users to break down complex visual queries or comparisons into multiple, less efficient prompts. The new functionality streamlines this process considerably if you happen to need the AI’s help for multiple images.

Gemini Multi Image Demo

On mobile platforms, both the Android and iOS system gallery pickers now support the selection of multiple photos, up to the new ten-image limit. This enhanced capability also extends to Gemini’s built-in camera feature, allowing you to capture multiple images sequentially without exiting the viewfinder before adding them to your prompt. The web version obviously doesn’t have a camera feature, but you can still upload up to ten images. And this is available on the 2.0 Flash model as well as on the (still experimental) Gemini 2.5 Flash and 2.5 Pro models.

While a lot of folks were probably fine with one-image prompts, this unlocks a whole new range of use cases for Gemini. You can use it to compare and contrast different items, or provide detailed context for complex questions by showing various angles or aspects of a subject. For instance, you could upload several photos of different products and ask Gemini to help you choose the best option based on visual features or written-out specifications. You could technically already do this by uploading multiple prompts with one image each and ask over and over, “How about this?” but this is both more time-efficient for you and probably a lot less resource-intensive for the AI. A win-win for everyone, if you ask me.

This should now be rolling out to everyone. Google advises users who don’t immediately see the new feature on mobile to force stop and restart the Gemini app, so if you’re not seeing this, this might be worth a shot. You can’t really do this on the web version, so if that’s still limited for you, you might want to wait a few days.