Join for quick access. Enter your email below and we'll send confirmation plus sign you up to our newsletter.
By submitting your information, you confirm you are aged 16 or over,
have read our
Privacy Policy
and agree to the
Terms & Conditions. Geographical rules apply.
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
You are now subscribed
Your newsletter sign-up was successful
Join the club
Get full access to premium articles, exclusive features and a growing list of member rewards.
An account already exists for this email address, please log in.
Raspberry Pi storybook uses AI to create stories with pictures on its eInk display
Coming up with a fresh bedtime story can be a challenge, so why not automate the process? That's exactly what maker and developer Thomas Valadez has done with his latest Raspberry Pi project. Using our favorite SBC, this Storybook Pi generates stories with a little help from AI and comes with a picture to go along with the story based on its description.
All of the generative AI happens locally on the Pi using a couple of open-source AI tools. Once the Pi generates a story and image, the data is formatted to display on a small eInk screen. This eInk panel offers a couple of colors, making for a more dynamic experience. Because it uses an eInk display, the power consumption is much lower and the image will remain on the screen should power drop.
(Image credit: Thomas Valadez)
Creating new images and stories isn't instantaneous. According to Valadez, it takes roughly five minutes to create a new story and picture. The eInk display also takes a little bit of time to refresh but if you aren't using it that often, this shouldn't be a big deal. However, the unique end result is well worth the wait.
To drive this project, Valadez is using a Raspberry Pi 5. Although you could get away with older models, the performance might not be as high. The screen is a 5.7-inch Inky Impression but you can use other displays in its place. Valadez recommends using a 32GB microSD card at least for this project as more space is useful for containing AI models.
Valadez was kind enough to share this project by making it open-source. As such, you can find the source code over at GitHub. You'll need to use a few tools along with Raspberry Pi OS to recreate it including both Ollama and Stable Diffusion.
If you want to get a closer look at this Raspberry Pi project, check out the official project page over at GitHub. Be sure to follow Valadez for more cool projects as well as for any future updates on this one.
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Ash Hill is a contributing writer for Tom's Hardware with a wealth of experience in the hobby electronics, 3D printing and PCs. She manages the Pi projects of the month and much of our daily Raspberry Pi reporting while also finding the best coupons and deals on all tech.
