This project uses the Stable Diffusion model to generate images from text prompts. It leverages the diffusers library.
pip install torch==2.2.2 diffusers==0.3.0 python-dotenv==1.0.1Rename a .env-example file to .env add your huggingface authentication token:
AUTH_TOKEN=your_huggingface_auth_tokenRun the script with a text prompt:
python3 main.py "A futuristic cityscape with neon lights"Optionally, specify an output path:
python3 main.py "A futuristic cityscape with neon lights" --output "city.png"| Prompt | Image |
|---|---|
| A futuristic cityscape with neon lights |  |
| A mystical underwater kingdom with glowing coral reefs and futuristic submarines, 4K |  |
| A quiet beach at sunset with waves gently touching the shore, 4K |  |
| A vintage motorcycle parked on an empty road surrounded by autumn trees, 4K |  |