https://github.com/letsdoitbycode/text-to-image-generator
The Text-to-Image Generator is an AI-powered web application that generates high-quality images from user-provided text prompts. Leveraging Hugging Face's Stable Diffusion model, the application transforms descriptive text into vivid and detailed visuals, making it ideal for creative projects, concept visualization, and artistic experimentation.
https://github.com/letsdoitbycode/text-to-image-generator
deep-learning gpu-computing neural-networks stable-diffusion text-to-image web-application
Last synced: 4 months ago
JSON representation
The Text-to-Image Generator is an AI-powered web application that generates high-quality images from user-provided text prompts. Leveraging Hugging Face's Stable Diffusion model, the application transforms descriptive text into vivid and detailed visuals, making it ideal for creative projects, concept visualization, and artistic experimentation.
- Host: GitHub
- URL: https://github.com/letsdoitbycode/text-to-image-generator
- Owner: letsdoitbycode
- Created: 2024-11-12T19:34:34.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-12T19:59:54.000Z (over 1 year ago)
- Last Synced: 2025-10-03T15:40:33.785Z (9 months ago)
- Topics: deep-learning, gpu-computing, neural-networks, stable-diffusion, text-to-image, web-application
- Language: Jupyter Notebook
- Homepage: https://letsdoitbycode-text-to-image-generator.hf.space
- Size: 984 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Text-to-Image Generator with Real-Time Emotion Detection: FaceVibe
### Project Link: - https://letsdoitbycode-text-to-image-generator.hf.space
The Text-to-Image Generator is an AI-powered web application that generates high-quality images from user-provided text prompts. Leveraging Hugging Face's Stable Diffusion model, the application transforms descriptive text into vivid and detailed visuals, making it ideal for creative projects, concept visualization, and artistic experimentation.
### Key Features
Key Objectives
- Seamless Text-to-Image Conversion: Allow users to input descriptive prompts and receive corresponding images that visually interpret the text.
- Accessible Web Interface: Provide an easy-to-use, interactive platform where users can generate images directly from their browser.
- Flexible Prompting for Visual Exploration: Enable users to experiment with different prompts to explore a wide variety of generated visualizations.
- AI-Powered Image Generation: Uses Hugging Face’s Stable Diffusion model to create high-quality images based on textual prompts.
- Interactive Image Generation: Users can experiment with different prompts to explore various visualizations.
### How It Works
- Text Input: Users enter a descriptive text prompt, like "a futuristic city skyline at sunset."
- Text-to-Image Model: The prompt is processed by Hugging Face's Stable Diffusion model, which uses embeddings and a generative neural network to create a corresponding image.
- Image Display: The generated image is displayed on the app interface, available for download.
### Installation
1. Clone the repository
```sh
git clone https://github.com/letsdoitbycode/Text-to-Image-Generator.git
cd Text-to-Image-Generator
```
3. Create a virtual environment and activate it:
```sh
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate`
```
4. Install the required packages:
```sh
pip install flask torch diffusers transformers accelerate gunicorn python-dotenv
pip install requirements.txt
```
5. API key setup for Application:
```sh touch .env ```
paste your API key in ```plaintext.env``` file as ```plaintext AUTH_TOKEN='API_KEY'```
```sh touch .gitignore ```
add ```plaintext .env``` in the file to secure the API key
To test the API key, follow below mentioned steps
```
### API Key Setup
To run the Text-to-Image Generator, you’ll need a Hugging Face API Token:
- Go to the Hugging Face website https://huggingface.co .
- Sign in or create an account.
- Navigate to Account Settings > API token and click Generate new token.
- Copy the generated token and add it in your Python code (StableDiffusionImage.ipynb) file in place of ```plaintext self.authorization_token = "" ```.
6. Run the Flask app:
```sh
python app.py
```
### Project Structure
```plaintext
YouTube-Video-Summarization-App/
│
├── app.py # Main Flask application
├── templates/
│ └── index.html # Main HTML file
├── static/
│ ├── style.css # CSS styles
├── .gitignore
├── StableDiffusionImage.ipynb # python file for the execution
├── requirements.txt # requirements for the project
└── README.md # This README file
```
## Demo Application Interface
## Contributing
Contributions are welcome! Please open an issue or submit a pull request for any changes or improvements.