Text-to-Image Streamlit App

Overview

This project is a Text-to-Image Streamlit App that allows users to generate images from text prompts using various models hosted on Hugging Face. The app provides an intuitive interface for generating and downloading images in PDF format.

Features

📝 Text Input: Users can input text prompts to generate images.
🖼️ Model Options: Multiple model options are available for generating images.
📄 Downloadable Images: Generated images can be downloaded in PDF format.
🤖 Hugging Face Integration: Utilizes Hugging Face hosted models APIs.
🧪 Experimentation: Experimented with Hugging Face diffusers and text_to_image pipelines.

Installation

To run this app locally, follow these steps:

Clone the repository:

git clone https://github.com/Santosh175/Text_to_image_web_app.git
cd Text_to_image_web_app

Install the required packages:
```
pip install -r requirements.txt
```
Run the Streamlit app:
```
streamlit run app.py
```

Usage

Open the app in your browser.
Enter a text prompt in the input field.
Select a model from the available options.
Click on the "Generate Image" button.
Download the generated image in PDF format.

Challenges

Real-time inferencing on limited compute resources is a significant challenge. Optimizing the performance and ensuring smooth user experience remains a priority.

Acknowledgements

A special thanks to Zhenna Lu for the inspiration throughout this project! 🙏

Contributing

Contributions are welcome! Please open an issue or submit a pull request for any improvements or suggestions.

License

This project is licensed under the MIT License.

Contact

For any questions or feedback, feel free to reach out to me on :- Linkedin Mail