Create a Children's book with AI – with illustrations
Hey together with wife we took part in AssemblyAI hackathon and although we didn't win we felt good enough about our inital MVP that we took it a bit further. You can describe your characters and give a title and however long/detailed description you want, the gpt-3 will generate a children's story from it, dall-e will generate images. Images are postprocessed with stable-diffusion custom model (for stylisation) and that's the final result. It's still early as it was done in about 2 weeks, but I count on your feedback. I am software engineer and did basically all of the engineering work…
In plain words
This tool generates illustrated children's books using AI. Users input character descriptions, a title, and story details, then GPT-3 creates the narrative while DALL-E generates images that are stylized through a custom Stable Diffusion model. The result is a complete illustrated story. Designed for parents, educators, and anyone wanting to create custom children's books, it combines multiple AI models into a streamlined workflow for rapid book creation.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey together with wife we took part in AssemblyAI hackathon and although we didn't win we felt good enough about our inital MVP that we took it a bit further. You can describe your characters and give a title and however long/detailed description you want, the gpt-3 will generate a children's story from it, dall-e will generate images. Images are postprocessed with stable-diffusion custom model (for stylisation) and that's the final result. It's still early as it was done in about 2 weeks, but I count on your feedback. I am software engineer and did basically all of the engineering work myself. Feel free to ask question regarding implementation plans, etc. cannot wait to learn what you think. I'll appriciate any feedback.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com


Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com


Launched alongside, December 2022
the whole month →
- OC
Life & fun · 2022 · obsidian.md
- PS
Commerce · 2022 · mprimi.github.io

Use generative AI to create future-facing videos
AI · 2022 · studio.d-id.com

- IW
Dev tools · 2022 · sqlfordevs.com