This project leverages the Stable Diffusion model to generate images from text prompts. It uses transformers and diffusers libraries, and features a user-friendly web interface created with Gradio. The entire project is implemented on Google Colab for easy access and execution.
- Text-to-image generation using Stable Diffusion
- Web-based user interface powered by Gradio
- Easy-to-use Google Colab implementation
To run this project:
- Open the Google Colab notebook
- Run all cells in order
- Access the Gradio interface via the provided link
- Enter your text prompt in the input field
- Click 'Generate' to create your image
- View and download the generated image
- Enter your text prompt in the input field
- Adjust any available parameters (if applicable)
- Click 'Generate' to create your image
- View and download the generated image
- Python
- Transformers
- Diffusers
- Stable Diffusion
- Gradio
- Google Colab
Contributions to improve the project are welcome. Please follow these steps:
- Fork the repository
- Create a new branch (
git checkout -b feature/AmazingFeature
) - Commit your changes (
git commit -m 'Add some AmazingFeature'
) - Push to the branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
Distributed under the MIT License. See LICENSE
for more information.
Project Link: https://github.com/ombhinav/Stable_diffusion