This adorable corgi isn't real, and Google's new text-to-image AI can do even more

A computer generated image of a corgi inside a house made of sushi
(Image credit: Google)

What you need to know

  • Google Imagen is a new AI-driven image generator that can create entire images from words.
  • Google showcased the technology with a release of a research paper that explains how it works, including several examples of its output.
  • There is no publicly available demo at this time and Google isn't releasing the source code just yet, citing concerns about societal impact.

AI image generation is nothing new, but Google's latest research paper displays an advancement of a kind we haven't seen since the first AI-driven image generators came about. In a nutshell, Imagen takes text and turns it into a realistic-looking image, driven completely by an AI that understands a large dictionary of words and what those words mean in a visual sense.

Google released its Imagen research paper alongside the explanation of the tool. Google says its own in-house developed benchmark, DrawBench, rates other image generation models based on human raters and show that the Google AI-powered Imagen produces superior results to those other models. The Imagen site showcases a number of different examples, a few of which we cherry-picked below.

Underneath the images above, you'll see the text that was used to generate that image with Google Imagen. In many cases, the text is extremely descriptive and is used to create a very specific end result that looks surprisingly realistic. Many other AI-driven image generators that you'll find online often create very abstract-looking imagery, as you might have seen on your favorite social media apps.

But, while Google has plenty of examples and an entire research paper to show how well Imagen works, it isn't making the technology publicly available just yet. In its explanation, Google sites societal concerns as the main reason for not letting users give it a shot just yet. Google says it believes that harmful, realistic imagery could be generated because the dataset used includes many uncurated words, many of which could be considered racist, derogatory, or otherwise harmful.

It's likely that Google will eventually release an open-source demo, as the company cites that being open-sourced could help prevent such issues. Specifically, Google says it won't release a demo or source until "further safeguards [are] in place." For now, you'll just have to enjoy the strangely surreal images Google provided on its site.

Nicholas Sutrich
Senior Content Producer — Smartphones & VR
Nick started with DOS and NES and uses those fond memories of floppy disks and cartridges to fuel his opinions on modern tech. Whether it's VR, smart home gadgets, or something else that beeps and boops, he's been writing about it since 2011. Reach him on Twitter or Instagram @Gwanatu