https://github.com/dzsezer/children-stories

OhanashiGPT is an application that generates personalized children's stories based on parameters like age and preferences. It narrates these stories using an AI-generated voice that mimics a parent, trained on their audio samples. The app also creates illustrations to accompany each story, providing a unique and engaging experience for children.
https://github.com/dzsezer/children-stories

coqui-tts llama3 llamacpp lora stable-diffusion stable-diffusion-xl-1

Last synced: about 1 month ago
JSON representation

OhanashiGPT is an application that generates personalized children's stories based on parameters like age and preferences. It narrates these stories using an AI-generated voice that mimics a parent, trained on their audio samples. The app also creates illustrations to accompany each story, providing a unique and engaging experience for children.

• Host: GitHub
• URL: https://github.com/dzsezer/children-stories
• Owner: dzsezer
• Created: 2024-08-27T08:44:52.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-08-29T12:17:23.000Z (3 months ago)
• Last Synced: 2024-09-30T03:38:53.235Z (about 2 months ago)
• Topics: coqui-tts, llama3, llamacpp, lora, stable-diffusion, stable-diffusion-xl-1
• Language: Jupyter Notebook
• Homepage:
• Size: 117 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# OhanashiGPT

![alt text](/built/image/The_Golden_Dragons_Ancient_Secret_Revealed.jpg "Title")

OhanashiGPT is an innovative application that creates custom stories for children based on input parameters such as age and other preferences. What sets this app apart is its ability to narrate these stories using an AI-generated voice that mimics a parent or other loved ones. Additionally, the app generates captivating images for each story, providing a unique and engaging experience for children.

# Childrens' Book Generation App

![alt text](/built/image/screenshot.png "Title")

The app runs as a web interface where you can customize your story settings. Hitting the "Generate Story" button will create a story, a cover picture and audio files that read the story to the user. You can find previously-generated stories in the "Explore" section. Previously-generated stories can be played with a different voice. It is also possible to add your own voice to the list of speakers.  

## Features

- **Custom Story Generation**: Stories tailored to the child's age and preferences.

- **AI Voice Synthesis**: Narrates stories using a familiar voice (e.g., parent's voice).

- **Image Generation**: Automatically creates illustrations that accompany the stories.

- **Interactive Experience**: Engaging storytelling for children, even when parents can't be there in person.

## Try out our app  

To run the app locally you have to install the depencies, download the models and start the server. You can find a detailed instruction [here](./app_instruction.md).

# DIY Tutorials

We also provide useful tutorials here so that you too can learn how to use AI models and also make your own models by finetuning them!

- [Finetuning large language models (LLMs) using Quantized Low-Rank Adaptation (QLoRA)](./finetuning/LLM_QLoRA)

- [Finetuning text-to-image (SDXL) using LoRA](./text-to-image/sd_xl/SDXL_LoRA_colab.ipynb)

- [Running text-to-image Flux1.schnell model locally](./text-to-image/flux1.schnell/DIY_text-to-image_flux1.schnell.ipynb)

- [Prompt engineering for text generation](./text-gen/Prompting_text_generation.ipynb)