Google has introduced an innovative feature to its Gemini AI chatbot, allowing users to create illustrated stories simply by providing descriptions. This new capability, known as the “Storybook,” generates 10-page narratives complete with text paragraphs that can be read aloud by Gemini, alongside accompanying illustrations.
Users can personalize their stories by specifying artistic styles, which range from claymation to anime and comic aesthetics. Additionally, Google enables the upload of personal photos or artworks for Gemini to reference, effectively allowing parents to turn their children’s artwork into unique storytelling experiences.
To explore these features, I prompted Gemini to craft a tale about a catfish trying to forge friendships in a new aquarium. As I navigated through the generated “pages,” I found the storyline about the fish attempting to reposition a marble somewhat underwhelming. However, the experience was typical of AI-created children’s literature—until an illustration depicted one fish sporting a human arm.
Another story generated by Gemini included a peculiar illustration of spaghetti sauce that resembled a cartoonish crime scene. Additionally, an image featuring a mother and son watching television showcased the screen on an incorrect side. A colleague even noted some AI-generated inconsistencies in Google’s promotional video for the feature, where a woman appears to be constructing a spaceship while making tapping noises with a wrench and an unidentified tool.
While I encountered some discrepancies in character designs, I did not observe any other significant errors in the additional stories generated by Gemini. However, when I uploaded my drawing of a cartoon cat, the chatbot did not seem to align with my artistic direction.
The new Storybook feature in Gemini is now accessible worldwide on both desktop and mobile devices, supporting all languages currently available in the Gemini platform.
