8000 GitHub - jielabs/langfun: A natural language-driven LM framework
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

jielabs/langfun

 
 

Repository files navigation

Storyboard

image

An AI-powered storyboard generator that converts scripts into visual storyboards using OpenAI and Google's Imagen API.

Features

  • Convert text scripts into detailed storyboards
  • Generate AI images for each scene using Google's Imagen
  • Interactive web interface built with Gradio
  • Visual descriptions and prompts for each scene
  • Complete JSON output of the storyboard

Setup

  1. Clone the repository:
git clone https://github.com/your-username/Storyboard.git
cd Storyboard
  1. Create a conda environment and install dependencies:
conda create --name storyboard python=3.10
conda activate storyboard
pip install -r requirements.txt
  1. Set up environment variables:
cp .env.template .env

Then edit .env and add your API keys:

  • OPENAI_API_KEY: Your OpenAI API key
  • GOOGLE_API_KEY: Your Google API key for Imagen

Usage

  1. Start the web interface:
python app.py
  1. Open the provided URL in your browser

  2. Paste your script into the text input

  3. Click "Generate Storyboard" to create your storyboard

The interface will display:

  • Generated images for each scene
  • Visual descriptions and prompts
  • Complete JSON output of the storyboard

Project Structure

  • app.py: Gradio web interface
  • generate_storyboard.py: Script to storyboard conversion
  • generate_image.py: Image generation using Google's Imagen
  • requirements.txt: Project dependencies
  • .env.template: Template for environment variables

Output

Generated files will be saved in:

  • output_script/: Generated JSON storyboards
  • output_img/: Generated images

License

MIT License

About

A natural language-driven LM framework

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%
0