LowinLi/stable-diffusion-streamlit

Quantized stable-diffusion cutting down memory 75%, testing in streamlit, deploying in container

46
/ 100
Emerging

Implements ONNX Runtime quantization (INT8) to reduce Stable Diffusion v1.4 memory footprint from 5.2GB to 1.3GB while maintaining image quality, with negligible inference overhead. Wraps the quantized pipeline in a Streamlit web interface featuring real-time progress tracking via Python threading and a gallery view for generated outputs. Ships as a Docker container for straightforward deployment with configurable runtime parameters like sampling steps and guidance scale.

No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

54

Forks

7

Language

Python

License

Last pushed

Feb 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/LowinLi/stable-diffusion-streamlit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.