Google has launched a new tool in its Gemini AI chatbot that allows creating illustrated stories by simply describing them. The feature, called Storybook, generates 10-page stories, each containing 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 certain artistic styles, such as those inspired by clay modeling, anime, comics, and more. Google also allows you to upload photos and other images for Gemini, such as uploading a child’s drawing and asking Gemini to create a story about it.
I just had to try these features for myself, so I asked Gemini to create a story about a catfish trying to make friends in a new aquarium. Flipping through the “pages,” I found that the story he generated about the aquarium’s inhabitants trying to move a marble pebble was rather lame. But otherwise, everything looked pretty standard for a children’s story created by artificial intelligence, until I came across an illustration in which a human hand was placed on one of the fish.
In another Gemini-generated story, a page depicting spaghetti sauce looked like a cartoon crime scene, and the image of a mother and son watching TV was turned upside down. My colleague Andrew Liszewski even noticed an AI-generated oddity in Google’s own video about the feature, where a woman builds a spaceship and makes “tap, tap, tap” sounds while holding a wrench and some other tool I can’t make out.
Aside from some inconsistencies in the character design, I didn’t notice any other glaring AI oddities in the other stories I asked Gemini to create. However, the chatbot didn’t seem to share my artistic vision when I uploaded an image of a cartoon cat I had drawn.