After announcing the new Imagen 3 image generation model at Google I/O in May, Google has now made the text-to-image model available to all Gemini users.
On Wednesday, Google said Imagen 3 “is now available to all Gemini users around the world.” As Google explained back when the model was announced, Imagen 3 comes with a number of significant improvements, including greater versatility and prompt understanding, higher quality image, and better text rendering than Imagen 2.
You don’t need to pay for Gemini Advanced in order to generate images with Imagen 3. Go to the Gemini website in your browser or the Gemini app on your phone and enter a prompt to get started. On my free account, when I asked Gemini to paint me a picture, the following message appeared: “Creating your image with Imagen 3…”
“Imagen 3 generates visually rich, high-quality images, with good lighting and composition,” said Google on its website. “It can accurately render small details like the fine wrinkles on a person’s hand, and complex textures like a knitted stuffed toy elephant.”
However, there are still limitations for free users. You can’t generate images of people unless you pay for Gemini Advanced, Business, or Enterprise. Otherwise, you’ll get an error message: “Generating images of people is only available in early access with Gemini Advanced. Get early access to new Gemini features when you subscribe to Advanced here.”
If you’re interested, you can try Gemini Advanced for one month for free. After that, you’ll have to pay $19.99/month, but you’ll get access to the Gemini 1.5 Pro model, priority access to new features, and a 1 million token context window.
