- Google will roll out its most advanced image generation model, Imagen 3, in most regions over the coming days.
- The tool will be available through Gemini apps on all platforms, and Google claims it will support all languages.
- Google will also roll out an early-access version of Imagen 3 that can generate images of people.
Google demoed Imagen 3, its most advanced text-to-image generator, at I/O this May. The tool recently made it to users as part of the Pixel Studio app on the Pixel 9 series, and you can even try it out with a Gemini Advanced subscription or Google’s AI Test Kitchen if you’re in the US. Over the coming days, Google will expand Imagen 3 availability to more users, and introduce Gemini Gems— a tool to customize Gemini and create AI experts on any topic.
Google claims that Imagen 3 sets a new standard for image quality and allows users to generate images in various styles with just a few words. The image generation model is capable of generating everything from photorealistic landscapes to textured oil paintings. The company previously asserted that it emphasizes delivering images with better detail, richer lighting, and fewer artifacts compared to other image generation models.