blog-post / README.md
dami1996's picture
README.md updated
e4c37fe
|
raw
history blame
2.32 kB
metadata
title: AI Blog Post Generator
emoji: πŸ“
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 3.23.0
python_version: 3.1
app_file: app.py
pinned: false
license: mit

AI Blog Post Generator

This is a web application that generates complete blog posts, including titles, content, cover images, and summaries based on user input. The app is built using Gradio and is designed to be deployed on Hugging Face Spaces.

Features

  • Generate blog post title using a specialized title generation model
  • Generate blog post content using GPT-2
  • Create a cover image for the blog post using Stable Diffusion
  • Summarize the generated article using BART
  • Simple and intuitive user interface

Models Used

  • Title Generation: fabiochiu/t5-small-medium-title-generation
  • Text Generation: gpt2
  • Image Generation: runwayml/stable-diffusion-v1-5
  • Summarization: facebook/bart-large-cnn

Setup and Deployment

  1. Fork this repository
  2. Set up a new Hugging Face Space (make sure to use a GPU-enabled instance)
  3. Configure the GitHub Actions workflow by adding your Hugging Face token as a secret named HF_TOKEN
  4. Update the deploy.yml file with your Hugging Face username and space name
  5. Push changes to the main branch to trigger automatic deployment

Local Development

To run the app locally:

  1. Clone the repository
  2. Install the required packages: pip install -r requirements.txt
  3. Run the app: python app.py

Note: Running multiple large language models and Stable Diffusion locally requires significant computational resources. A GPU is strongly recommended for reasonable performance.

Usage

  1. Enter a topic or idea for your blog post in the input text box
  2. Click the "Submit" button
  3. Wait for the models to generate the title, article, cover image, and summary
  4. Review the generated content and use as desired

Contributing

Feel free to open issues or submit pull requests to improve the application. We welcome contributions of all kinds, including bug fixes, feature additions, and documentation improvements.

License

This project is open source and available under the MIT License.


For more information on Hugging Face Spaces configuration, please refer to the Spaces Configuration Reference.