Imagen 3 provides advanced image generation capacities that are delivered with guarantees and adhere to our product design principles. Through a wide range of landmarks, Imagen 3 works favorably compared to other models for the generation of available images. And as with Imagen 2, we use Synthetic, Our tool for the watermark of the images generated by AI.
Our design principles are clear: from start to finish, you stay in control of the creative process. If the initial image you get does not meet your expectations, simply tell Gemini what you want to change and this will give you a new image.
In the coming days, we will also start to deploy the generation of people of people, with an early access version for our users Gemini Advanced, Business and Enterprise, from English. We have worked to provide technical improvements to the product, as well as improved evaluation sets, red and clear equipment exercises Product principles.
With Imagen 3, we have made significant progress in the provision of a better user experience when generating people of people. We do not support the generation of photorealistic and identifiable individuals, representations of minors or excessively bloody, violent or sexual scenes. Of course, as with any generative AI tool, all the images that the Gemini create will not be perfect, but we will continue to listen to the comments of the first users while we continue to improve. We will gradually deploy this, aimed at bringing it soon more users and languages.
To be among the first to discover these new features, try Advanced gemini today or register for Gemini for the workspace.