How to create AI images for free using Google Gemini

Earlier this month, Google introduced the Imagen 2 language model, enhancing Gemini (formerly Bard) with the AI image generator feature. This update enables users to generate images based on prompts on both the Gemini web platform and the newly launched Android app, as well as on the Google app for iOS.

The image generation process on Gemini is facilitated by the Imagen 2 language model, allowing users to input simple prompts. However, some users reported instances where the AI-generated images depicted people of color in response to prompts like “generate a picture of a Swedish woman” or “generate a picture of an American woman.”

In response to these concerns, Google acknowledged the unintended outcomes and stated that they did not intend for Gemini to exclude or misrepresent any particular group. As a result, they temporarily disabled the image generation feature for people and committed to improving it significantly through extensive testing before reactivating it.

Nevertheless, Gemini can still generate images for prompts unrelated to depicting people. To utilize Gemini’s image generator, users can follow these steps:

1. Visit gemini.google.com in your web browser.
2. Enter a descriptive image prompt in the text box to enhance the results.
3. Click “Generate,” and Gemini will produce a gallery of AI-generated images based on the prompt.
4. Select “Generate more” beneath any images to obtain additional variations.
5. Click on any thumbnail image to view a full-size version, and navigate through the images using on-screen arrows or the “Show previous image/Show next image” options.