Imagen 3 brings advanced image generation capabilities that come with built-in safeguards and adhere to our product design principles. Across a wide range of benchmarks, Imagen 3 performs favorably compared to other image generation models available. And as with Imagen 2, we use SynthID, our tool for watermarking AI-generated images.
Our design principles are clear: From start to finish, you remain in control of the creative process. If the initial image you get doesn’t meet your expectations, simply tell Gemini what you’d like to change and it’ll give you a new image.
Over the coming days, we’ll also start to roll out the generation of images of people, with an early access version for our Gemini Advanced, Business, and Enterprise users, starting in English. We’ve worked to make technical improvements to the product, as well as improved evaluation sets, red-teaming exercises and clear product principles.
With Imagen 3, we’ve made significant progress in providing a better user experience when generating images of people. We don’t support the generation of photorealistic, identifiable individuals, depictions of minors or excessively gory, violent or sexual scenes. Of course, as with any generative AI tool, not every image Gemini creates will be perfect, but we’ll continue to listen to feedback from early users as we keep improving. We’ll gradually roll this out, aiming to bring it to more users and languages soon.
To be among the first to experience these new features, try Gemini Advanced today or sign up for Gemini for Workspace.