All Gemini users can now generate images using Imagen 3. Along with Gems, Imagen 3 was revealed in August after being seen in advance at I/O 2024 in May. According to Google, Imagen 3 provides more text rendering, better prompt understanding, higher quality photos, and increased adaptability.

In a post on X by the Google Gemini App, Google explained, “Imagen 3 is our highest quality image generation model yet, bringing an even higher degree of photorealism, better instruction following, and fewer distracting artefacts than ever before,” 

Users must give prompts beginning with “draw,” “generate,” or “create” and specify the desired style—such as photorealistic, watercolour, painting, or cartoon illustration—in order to use the capabilities. Gemini notifies customers that it is using Imagen 3 to create an image, which they can download with a watermark placed by SynthID. “SynthID watermarks and identifies AI-generated content by embedding digital watermarks directly into AI-generated images, audio, text, or video.” explains Google.

People’s image generating is currently not available to users for free. Early access to this feature was launched by Google in May for Gemini Advanced, Business, and Enterprise users in the English language.

In the US, Google is rolling out the “Ask Photos” tool to a limited number of customers. This functionality, which is powered by Gemini, is being rolled out via a server-side update within the Google Photos app, thus users’ version of Google Photos is irrelevant. By utilising Google’s Gemini AI models, Ask Photos enables users to ask questions in natural language straight within Google Photos.