Gemini Can Now Generate Interactive Images Directly in the Chat

Gemini has always been good at generating images through Nano Bananabut Google recently launched a new way to understand a topic when chatting with the AI ​​tool. Now when you ask Gemini to visualize something, you won’t just get a static image, but rather an interactive image.

The new feature will generate a dynamic visualization when an image is not enough. Google says you can ask Gemini to “show me” or “help me visualize” a specific topic, and the visual will be created when you click the “show me visualization” button that appears.

I tested this feature by asking Gemini how the Moon orbits the Earth and then showing me how a car engine works. Both times, an interactive visual was created that explained much more than a single image could.

For viewing the moon’s orbit, there was a slider to adjust the speed of the orbit, as well as other adjustments to fine-tune the view. Similar features also appeared in the visualization of the car’s engine. I was able to change the playback of the animated car engine or manually adjust the view so that it illustrated each step of the process.

Anthropic announced a very similar functionality for Claude in March, and the results were impressive. However, there is no way to save visuals in Gemini, like you can with Claude. It remains to be seen if and how these interactive simulations will improve over time.

Google did not immediately respond to a request for comment.

The new Gemini feature is rolling out globally to all users, but is currently not available for Education or Workspace accounts. Visualizations will only be generated when using the Pro template.