The Multimedia Content Generator is an innovative project leveraging the capabilities of OpenAI's GPT-4 and DALL-E-3 models, along with the Replicate API. It is designed to autonomously create a cohesive multimedia story. Given a user prompt, the system generates a narrative, accompanying voiceover, illustrative images, and synthesized videos, culminating in an integrated multimedia experience.
- Story Generation: Utilizes OpenAI's GPT-4 model to craft compelling stories from user-provided prompts.
- Voiceover Creation: Converts the generated story into a voiceover using OpenAI's Text-to-Speech API.
- Image Generation: Produces vivid images corresponding to specific story segments through OpenAI's DALL-E-3 model.
- Video Synthesis: Transforms the generated images into dynamic videos via the Replicate API.
- Multimedia Integration: Seamlessly merges the voiceover and videos into a unified video narrative.
- Clone the Repository:
git clone https://github.com/dombom123/x-fiction.git - Install Dependencies: Run
pip install -r requirements.txtto install the necessary Python packages.
- Configure API Keys: Create a
.streamlit/secrets.tomlfile like the provided example file.streamlit/secrets.example.toml
Start the Streamlit Frontend:
streamlit run x-main.py
The script processes your prompt to generate a story, voiceover, images, and videos, ultimately combining them into a single multimedia file.
Your contributions can help grow and improve this project! To contribute:
- Fork the Repository: Create your own fork of the project.
- Create a Feature Branch: Work on your new feature in a separate branch.
- Commit Your Changes: Add meaningful commit messages describing your changes.
- Push to the Branch: Upload your changes to your fork.
- Open a Pull Request: Submit a pull request for review.
Thank you for your interest in contributing to the Multimedia Content Generator!
This project is released under the [MIT License].
For inquiries or collaboration, reach out via:
- Email: [email protected]