Google is rolling out a new image generation AI model, Imagen 4, which claims to provide higher quality results than its previous image generator, Imagen 3.
Announced Tuesday at Google I/O 2025, Imagen 4 is capable of rendering “fine details” like fabric, water droplets and animal fur, says Google. This model handles both photorealistic and abstract styles, create images in aspect ratio ranges, and can create resolutions of up to 2k.
“Imagen 4 is (a) a big step forward in quality,” said Josh Woodward, head of Google’s lab group, during a press conference. “We also (paid) a lot of attention and modifications on how to generate text and terrain, so creating slides and invitations is great.
From ChatGpt’s virus tools to Midjourney’s V7, there’s no shortage of AI image generators. They are all relatively sophisticated, customizable, and allow you to create high-quality AI artwork. So, why does Imagen 4 stand out from the crowd?
According to Google, Imagen 4 is faster – faster than Image 3. And it’s quicker soon. In the near future, Google plans to release a variant of Imagen 4, which is up to 10 times faster than Imagen 3.
Imagen 4 is available as of this morning on Gemini app, Google’s Whisk and Vertex AI platforms, and on Google Workspace, including Google Slide, Vids, Docs and more.