CoolFace
Apppublic

Pablinho/bedtime-stories

sourceHugging Faceupdated 2y agoView on Hugging Face
1likes
App README

Bedtime Stories Generator

This project is an AI-powered Children Story Generator that creates unique stories based on uploaded images. It uses image captioning and large language models to generate engaging stories for children.

Features

  • —Upload an image to generate a story
  • —Choose from multiple language models for story generation
  • —User interface built with Gradio
  • —Handles various image formats

Tech Stack

  • —Python
  • —Gradio for the web interface
  • —Hugging Face Transformers for image captioning
  • —LangChain for interfacing with language models
  • —PIL (Python Imaging Library) for image processing

Installation

  1. 1.Clone this repository:
   git clone https://github.com/yourusername/kids-story-generator.git
   cd kids-story-generator
  1. 1.Install the required dependencies:
   pip install -r requirements.txt

Usage

  1. 1.Run the application:
   python app.py
  1. 1.Open your web browser and navigate to the URL provided in the terminal (usually http://localhost:7860).
  1. 1.Upload an image or use one of the provided examples.
  1. 1.Select a language model from the dropdown menu.
  1. 1.Click "Submit" to generate a story based on the image.

Deploying to Hugging Face Spaces

This project is designed to be easily deployed to Hugging Face Spaces. To deploy:

  1. 1.Create a new Space on Hugging Face.
  2. 2.Connect your GitHub repository to the Space.
  3. 3.Make sure all files, including the assets folder with example images, are included in your repository.
  4. 4.Set the Space SDK to "Gradio".
  5. 5.The requirements.txt file should automatically install all necessary dependencies.

Project Structure

  • —app.py: Main application file with Gradio interface
  • —brain.py: Contains the StoryGenerator class with core functionality
  • —assets/: Folder containing example images
  • —requirements.txt: List of Python dependencies

Contributing

Contributions to improve the project are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.