This project demonstrates a text-to-image model using Gradio, a Python library for creating customizable web-based user interfaces for machine learning models.
To run this project, you need to install the following Python libraries:
- Gradio
- Pillow
- torch
- torchvision
You can install them using the following command:
pip install gradio Pillow torch torchvision
To run the Gradio interface, simply run the text_to_image_gradio.py
file using Python:
python text_to_image_gradio.py
This will start a Gradio interface that allows you to enter text and generate an image based on the text using the text-to-image model.
This project was inspired by the DALL-E 2 OpenAI paper and codebase by lucidrains. The text-to-image model used in this project was trained using the Text-to-Image Synthesis example in the DALL-E 2 codebase.