A simple, interactive Streamlit web app that generates images from textual prompts using the Stable Diffusion v1.5 model from Hugging Face 🤗 diffusers.
https://text-to-imagez.streamlit.app
| 
| 
|
- ✅ Generate images from natural language prompts
- ✅ GPU support using
torch.cuda - ✅ Fast image generation with optimized inference settings
- ✅ Clean, responsive Streamlit UI
- ✅ Efficient memory usage with
attention_slicing
| Tech | Purpose |
|---|---|
| Streamlit | Frontend UI for user interaction |
| Hugging Face 🤗 diffusers | For loading and running Stable Diffusion |
| PyTorch | Deep learning framework |
| Stable Diffusion v1.5 | Text-to-image generation model |
| PIL | Image handling and display |
git clone https://github.com/yourusername/ai-image-generator.git
cd ai-image-generator
python -m venv venv
source venv/bin/activate # or venv\Scripts\activate on Windows
pip install -r requirements.txt