2 Sources
[1]
Google Gemini wants to transform your memories into illustrated storybooks
T-Mobile is automatically 'upgrading' Magenta Max customers to its new Go5G plans Instead of making up whimsical stories in your head, Gemini wants to help you bring your ideas to life in the form of illustrated storybooks. Up until now, you could share ideas with Gemini and tell it to whip up a simple story with it. Narrowing down prompts and specifying details could yield more personalized results. Now, Google is further enhancing the storybook experience, allowing for even more personalization, read-aloud narration, and even custom art to go along with your stories. Concrete hints about the feature first started emerging last month, and the wait now seems to be over. Initially believed to be hidden behind a gem, you don't really need to go into Gemini's dedicated gem manager section to access the feature. Instead, creating a 'storybook' is as simple as navigating to the gemini app and typing away your imaginative prompt in the text box. "Simply describe any story you can imagine, and Gemini generates a unique 10-page book with custom art and audio," wrote the tech giant in a blog post announcing the feature. To further personalize the storybook and its illustrations, users are free to point out specific details and share photos and files for the AI tool to draw inspiration from. Never run out of bedtime stories Close In my experience using the feature, Gemini is normally able to generate a complete storybook in roughly a minute, complete with a cover page and ten distinct pages of content. Although Google didn't explicitly mention it, it is likely that it's using Veo 2 to power the illustrations, with Google's text-to-speech model taking over the load of narration. Users can generate storybooks in multiple languages and styles, including pixel art, comics, claymation, crochet, and even coloring book styles. The artistic possibilities are truly endless with this one, especially since you have the freedom to share your own photos. Some storybook examples and usecases shared by the tech giant include: Understanding complex topics: Create a story that explains the solar system to my 5 year old. Teaching lessons in an interactive manner: Teach a 7-year-old boy about the importance of being kind to his little brother. My son loves elephants so let's make the main character an elephant. Bring your own personal artwork to life: Upload an image of a kid's drawing and modify this example prompt for your use case: "This is my kid's drawing. He's 7 years old. Write a creative storybook that brings his drawing to life." Turn your own memories into engaging stories: Upload photos from your family trip to Paris and create a personalized adventure. The functionality is rolling out now on both desktop and mobile. As of writing, the feature has only been rolled out to me on the web.
[2]
Gemini's Storybook Feature Lets You Generate a 10-Page Illustrated Book
These can be generated on both the website and the mobile apps Google added a new quality-of-life feature to its Gemini chatbot on Tuesday. The artificial intelligence (AI) chatbot can now generate custom illustrated storybooks based on text prompts, uploaded images or documents. Users can also specify the style of the artwork in the storybook, as well as instruct Gemini to use specific names of characters, settings, or even plot points. The Mountain View-based tech giant designed the feature for young children who enjoy reading bedtime stories. It is available to all users globally on the website and mobile apps. In a blog post, Google detailed the new feature, which is rolling out to all Gemini users, including those on the free tier. Storybook creation is available directly within the chatbot's interface, and users can start a prompt with "Create/Generate a storybook..." followed by the topic of the story and the age of the readers. Additionally, users can also mention a specific character name, a setting, and the art style. Storybook in Gemini supports various art styles, including pixel art, comics, claymation, crochet, and colouring books. These can be generated in 45 languages, and each story can have up to 10 pages. Each page will have text on the right side and a related artwork on the left side. The feature also comes with audio narration, if users prefer to hear the story rather than reading it. The voice is robotic and not similar to the natural-sounding voice one hears in Gemini Live. Gadgets 360 staff members were able to test out the feature, and the chatbot was able to generate a storybook in a couple of minutes, complete with a title page and art, and 10 pages of story. It was also able to adhere to all the nuances (genre, setting, use of a particular item, etc) in the prompt. We also did not notice any inconsistencies or hallucinations in the AI-generated images. Google says users can also upload their photos to create a story where the art features them instead of randomised characters. Similarly, users can also upload documents of their written stories and turn them into an illustrated book using AI. Apart from reading children bedtime stories, the tech giant says the feature can also be used to teach young students complex topics from their syllabus.
Share
Copy Link
Google has launched a new feature for its Gemini AI that allows users to create personalized, illustrated storybooks complete with narration, offering a blend of creativity and technology for storytelling.
Google has introduced a groundbreaking feature to its Gemini AI platform, allowing users to create personalized, illustrated storybooks with just a few prompts. This innovative tool, which combines advanced text generation with AI-powered illustrations, marks a significant step in the intersection of artificial intelligence and creative storytelling 1.
The storybook creation process in Gemini is remarkably straightforward. Users can simply navigate to the Gemini app and type their imaginative prompt into the text box. The AI then generates a unique 10-page book, complete with custom art and audio narration. The entire process typically takes about a minute, resulting in a cover page and ten distinct pages of content 1.
One of the key strengths of this new feature is its high degree of customization. Users can specify details, share photos, and even upload files to inspire the AI's creative process. The system supports multiple languages and various artistic styles, including pixel art, comics, claymation, crochet, and coloring book styles 2.
Source: NDTV Gadgets 360
While Google hasn't explicitly confirmed, it's likely that the illustrations are powered by Veo 2, with Google's text-to-speech model handling the narration. The feature is available on both desktop and mobile platforms, with the rollout currently in progress 1.
Google envisions a wide range of applications for this technology:
Source: Android Police
The storybook feature is being rolled out to all Gemini users globally, including those on the free tier. It supports 45 languages and is accessible directly within the chatbot's interface on both the website and mobile apps 2.
This development represents a significant leap in AI-assisted creativity, blurring the lines between human imagination and machine-generated content. As the technology continues to evolve, it could have far-reaching implications for education, entertainment, and personal expression, potentially revolutionizing how we create and consume stories in the digital age.
Summarized by
Navi
[2]
Microsoft rolls out OpenAI's latest GPT-5 model across its Copilot suite, including Microsoft 365, GitHub, and Azure AI Foundry, promising enhanced reasoning and performance in AI-assisted tasks.
6 Sources
Technology
13 hrs ago
6 Sources
Technology
13 hrs ago
Tesla disbands its Dojo supercomputer team, with project lead Peter Bannon departing. The move marks a significant shift in Tesla's AI and self-driving strategy, impacting its in-house chip development efforts.
10 Sources
Technology
5 hrs ago
10 Sources
Technology
5 hrs ago
Roblox introduces an open-source AI system called Sentinel to detect and prevent child endangerment in its platform's chat feature, addressing growing concerns about online predators targeting young users.
8 Sources
Technology
21 hrs ago
8 Sources
Technology
21 hrs ago
OpenAI launches GPT-5, its most advanced AI model yet, featuring improved vibe coding abilities that allow users to create custom applications using natural language prompts.
2 Sources
Technology
13 hrs ago
2 Sources
Technology
13 hrs ago
OpenAI's GPT-5 launch sparks a public exchange between Elon Musk and Satya Nadella, highlighting the intensifying competition in AI development and integration across major tech platforms.
2 Sources
Technology
5 hrs ago
2 Sources
Technology
5 hrs ago