Google Gemini Revives AI-Generated People Feature with Imagen 3

Google Revives Image Generation Feature in Gemini AI Chatbot

Google is reintroducing the capability for users to generate images of people through its Gemini AI chatbot, following a brief suspension of the feature earlier this year. The decision comes on the heels of various user complaints regarding historically inaccurate images produced by the tool, which included controversial representations such as racially diverse Nazis.

Early Access Launch

In a recent announcement, Google confirmed that an early access version of this image generation capability would be made available to Gemini Advanced, Business, and Enterprise users in English over the coming days. This functionality will be powered by Imagen 3, the latest iteration of Google’s AI text-to-image generator.

What is Imagen 3?

Imagen 3 was launched quietly through Google’s AI Test Kitchen earlier in the month and is now set to be integrated into Gemini AI across all supported languages. The advanced tool boasts the ability to create a wide variety of visual content, ranging from photorealistic landscapes to textured oil paintings, all generated with only a few descriptive words from the user.

Addressing Previous Concerns

Google had initially paused Gemini’s image generation of people in February due to the prevalence of historically inaccurate results. With the upgraded Imagen 3 model, the company assures that it has implemented built-in safeguards aimed at improving the accuracy of generated images. As stated by Dave Citron, Google’s senior director of product management for Gemini, the new model has shown promising performance compared to other image generation options currently available.

What Gemini Users Must Know

• Gemini will not permit the creation of photorealistic images of public figures.
• Content involving minors is strictly prohibited.
• Generated images depicting gory, violent, or sexual themes will not be allowed.

Citron emphasized that while not every image generated by Gemini will achieve perfection, the company is committed to listening to feedback from early access users to further refine the tool.

Comparison with Remagine Feature

It’s essential to distinguish this feature from Google’s new Remagine functionality, which enables users to add AI-generated elements to photographs taken with the company’s latest lineup of Pixel 9 smartphones. This contrasting feature underscores Google's broader strategy to integrate AI technologies into its consumer offerings.

Looking Ahead

Google plans to extend the ability to create AI-generated images of people to a broader audience and include support for additional languages shortly. This expansion reflects Google’s ongoing efforts to enhance its AI capabilities while managing the complexities of accurate and responsible image generation.

For more information on these updates and to keep abreast of future releases, stay connected with Google’s official channels and related tech news sites.