Google announced that it has updated the artificial intelligence (AI) image generation model on its Gemini app after a months-long pause. Google had paused the feature earlier this year amid reports of historically inaccurate images. Google affirmed in its statement that it will move to the most advanced model for creating images via AI text-to-image generator Imagen 3, which was first revealed at the developer conference last May, as the image creation commands in Gemini will be executed via this latest model. The company explained that this upgrade will restore the ability to create images of legal persons through AI, which had stopped in the past. The updated version also features the ability to create photorealistic landscapes, and textured oil paintings through text commands describing what is required in the image, using a brief description consisting of only a few words. Over the coming days, Google will start to roll out an early access version for paid Gemini users in English. Source: Qatar New s Agency
Thursday, November 07, 2024