Google rolled out a new tool within its Gemini AI chatbot that lets you create an illustrated story by simply describing it. The feature, called “Storybook,” generates 10-page stories, each with a short paragraph of text that Gemini can read aloud, along with an accompanying illustration.

You can customize your story by asking Gemini to use specific art styles, such as ones inspired by claymation, anime, comics, and more. Google also lets you upload photos and other images for Gemini to reference, like uploading a child’s drawing and asking Gemini to create a story about it.

I just had to try out these features for myself, so I first asked Gemini to create a story about a catfish struggling to make friends in a new aquarium. As I flipped through the “pages,” I found that the plot it generated about the tank’s inhabitants trying to move a marble was pretty lame. But other than that, everything seemed pretty standard for an AI-generated children’s story, until I came across one illustration that put a human arm on one of the fish.

Another Gemini-generated story made a page involving spaghetti sauce look like a cartoon crime scene, while an AI image of a mother and son watching TV put the screen on the wrong side. My colleague Andrew Liszewski even spotted an AI-generated oddity in Google’s own video about the feature, which shows a woman building a spaceship and making “tap, tap, tap” noises while holding a wrench and some other tool I can’t make out.

Besides coming across some inconsistencies in character designs, I didn’t spot any other blatant AI weirdness in some of the other stories I had Gemini create. However, the chatbot didn’t seem to share my artistic vision when I uploaded an image of a cartoon cat that I drew.

The Gemini Storybook feature is available globally on desktop and mobile, including in all the languages Gemini currently supports.