Christmas is approaching, and while stores offer a vast array of toys, some parents seek a more personal gift. One option is a custom-made picture book. However, not everyone has a knack for creating child-friendly stories or illustrations, not to mention the time required.
Thanks to generative AI, creating a picture book has become easier. AI tools like ChatGPT can write stories, and AI-driven image generators can create illustrations. Here’s a simplified guide to creating a picture book using AI.
Creating a Children’s Christmas Story with AI
We used ChatGPT and Midjourney to create a Christmas story for children. The result may not win any awards, and the illustrations might need some tweaking, but it demonstrates that you can quickly generate a picture story using AI. The amount of fine-tuning is up to you.
Writing a Child-Friendly Story with ChatGPT
Start by crafting a story for your picture book. You can write it yourself or let ChatGPT do the work. If using ChatGPT, specify what the story should be about in your prompt. You can also include names or details relevant to your children.
For example, we used the prompt: “Write a children’s story about a boy named Joshua who has a Christmas adventure.” You can add more details like settings, characters, or objects to refine the story. If the result isn’t satisfactory, you can ask ChatGPT to generate a new response.
Editing the story yourself can also help resolve issues with image generation, as AI image generators sometimes struggle with certain prompts. Adjusting the story can save time if an image doesn’t turn out as expected.
Illustrating a Picture Book with Midjourney
There are several AI-powered image generators available for illustrating your story. We used Midjourney for our example. Regardless of the tool, you’ll need to ensure consistency in character depiction across all images.
One approach is to provide Midjourney with a text prompt and images, ensuring your character appears consistently. We created our main character in various poses using Midjourney.
Our prompt was: “little boy character, multiple poses and expressions, children’s book illustration style, simple, cute, full color, green shoes, short blonde hair, hoodie, blue pants, flat color, –no outline.” It’s crucial to specify that you want the character in different poses and expressions. You can choose the character’s attributes, such as hair color and art style.
After creating your character, download the image with different poses and separate them using an image editing program. Upload these individual images to Discord by dragging and dropping or using the upload button.
Next, copy the URLs of all images, start a new image prompt with the /imagine command, and paste all URLs separated by spaces. Then, include the original prompt with a modification.
Replace “multiple poses and expressions” with a prompt describing the specific scene. If none of the generated images are satisfactory, retry or adjust your prompt until you get a suitable image.
Experimentation is key. Zooming out can sometimes help. Additionally, in Midjourney, you can use the –iw command to specify the importance of images relative to the text prompt, with a value from 0 to 2. A lower value gives more weight to the text prompt compared to the images. While you don’t want to stray too far from the image templates, adjusting this value can be beneficial.
Creating a picture book with AI can be an exciting project, offering a personalized gift option for children. With tools like ChatGPT and Midjourney, the process becomes accessible and manageable, allowing you to focus on creativity and personalization.