/cdn.vox-cdn.com/uploads/chorus_asset/file/25592596/imagen_3_ai_person.png?w=696&resize=696,0&ssl=1 "Google Gemini will let you re-create AI-generated humans")
/cdn.vox-cdn.com/uploads/chorus_asset/file/25592596/imagen_3_ai_person.png?resize=1200,628&ssl=1&description=Google+Gemini+will+let+you+re-create+AI-generated+humans){kind=link}
Google is once again allowing its users to generate images of people using its Gemini AI chatbot after pulling the feature earlier this year amid reports of historically faulty depictions such as racially diverse Nazis. announcementGoogle says it will roll out early access to the feature to Gemini Advanced, Business, and Enterprise users in English in the “coming days.”
This update will be powered by Imagen 3, the latest version of Google’s AI text-to-image generator. Google quietly launched Imagen 3 via its AI Test Kitchen earlier this month, and it’s now coming to Gemini in all languages. The improved tool is capable of generating everything from photorealistic landscapes to textured oil paintings with descriptions of “just a few words.”
This feature should not be confused with Google’s modern Remagine feature, which lets you incorporate AI elements into photos taken with the company’s modern Pixel 9 phones.
In addition, Gemini won’t let users create photorealistic images of public figures; content involving minors; or gore, violence, or sexual scenes. “Of course, not every image created by Gemini will be perfect, but we’ll continue to listen to feedback from Gemini Advanced early access users as we continue to improve,” Citron adds. Google plans to expand AI-generated characters to more users and languages soon.