How to generate images with Gemini in Google Docs

Creating visual content in Google Docs just became easier, thanks to Gemini’s new built-in image generation feature. This integration allows users to design custom visuals directly within their documents, eliminating the need to switch between applications or external AI tools. Powered by Google’s Gemini, the tool offers a seamless way to produce illustrations, diagrams, or stylised artwork without disrupting your writing flow.

Accessing the image generator

To get started, open a Google Doc and place your cursor where the image should appear. Then, go to the Insert menu, click Image, and choose Generate image. This opens the Gemini panel, where you can begin crafting your prompt.

Writing your image prompt

In the Gemini sidebar, type a detailed description of the image you want to create. Include specifics like setting, lighting, colors, and style to help the model generate more accurate results. For example, “a glowing city skyline at night with purple clouds” will yield much better images than simply “city.”

Customizing style and format

Before hitting create, users can refine the visual style. Gemini offers options such as cartoon, photorealistic, or watercolor, as well as image formats like square, landscape, or portrait. These help adapt the image to fit your document’s needs more effectively.

Selecting and inserting your image

Once you click Create, Gemini will show four versions of your image. Choose the one that best matches your intent, or click View more for additional variants. When satisfied, simply click to insert the image into your document, where it can be resized or moved as needed.