Coding in Android Studio has just gotten better and richer as the Gemini AI on the platform now supports multimodal inputs, allowing developers to attach images directly in the prompts, and build higher-quality applications.
Indeed, Gemini’s multimodal capabilities allow Gemini in Android Studio to understand simple wireframes and transform them into working Jetpack Compose code, and now they include an image attachment icon in the Gemini chat window, according to an Android Developers Blog post on March 14.
New uses for Gemini in Android Studio
Specifically, developers can now attach JPEG or PNG files to their prompts and Gemini will respond to the visual information, with the best results provided in response to images with strong color contrasts. Consequently, use cases include rapid UI prototyping and iteration, in which a simple wireframe or high-fidelity mock of an app’s UI can transform into working code.
Additionally, Gemini in Android Studio can now provide diagram explanation and documentation towards deeper insights into complex architecture or data flow diagrams, as well as for UI troubleshooting, where you can capture screenshots of UI bugs and ask Gemini for solutions.
What is the latest Android Studio version?
Android Studio was first announced in May 2013 and has since gone through numerous improvements and release versions, the most recent one being Android Studio Meerkat 2024.3.1. Also, the newest multimodal image support is available in its latest Canary build.
Elsewhere, Gemini isn’t just useful for writing, editing, and correcting code. As it happens, Google DeepMind has recently introduced a new platform for building robots called Gemini Robotics, which is based on Gemini 2.0 and is an advanced vision-language-action (VLA) model.