Gemini AI Prompts Now Accept Multiple Images : Here’s How It Works?

Gemini, Google’s AI service, is getting new features that allow users to upload multiple images in a single prompt, making it easier to interact with the system. Such an upgrade allows users to get more nuanced results because now the system is able to analyse several images at the same time. Multi-image prompts enable greater flexibility whether users want a deeper comparison of product sketches, need design inspiration, or want to study data visualisation. This is a new paradigm for fulfilment of user requests and significantly increases the competitive potential of Gemini in the context of other advanced multi-modal AI services and instruments. This is intended to enhance the power, adaptability, and simplicity of Gemini, especially for creators, professionals, and researchers who depend on advanced visual artificial intelligence interfaces.

Gemini AI Multiple Images Prompt Support

The update includes an AI prompt functionality redesign, allowing users to submit up to ten images per prompt on Gemini's mobile and web applications.

Gemini used to allow the user to only attach one image per prompt. If a user tried to add another image, Google would show a warning that stated, “Replace current? — Adding a new image will remove the current one.”

The system gallery pickers for Android and iOS now allow you to choose as many as 10 pictures. Gemini’s built-in camera also allows this. After capturing a picture, the viewfinder can be accessed again. If you do not see this option, make sure to close the mobile app.

Through gemini.google.com, Google has the limit of uploading 10 images: “Some of your files could not be uploaded because you can only upload 10 attachments at a time.” This applies to all current models: 2.0 Flash, 2.5 Flash, and 2.5 Pro.

This afternoon’s wide rollout announcement was preceded by a gemini feature request thread, where Josh Woodward encouraged users to share what most commonly triggers grumpiness.