Xiuyu-Li/q-diffusion

[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.

40
/ 100
Emerging

This project helps machine learning engineers and researchers optimize their diffusion models for image generation. It takes a full-precision diffusion model and converts it into a lower-precision, more efficient version without significant loss in image quality. The output is a "quantized" model that generates high-quality images much faster, ideal for deploying image generation systems more efficiently.

371 stars. No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher working with diffusion models for image synthesis and need to significantly speed up image generation or reduce computational requirements without sacrificing quality.

Not ideal if you are not familiar with machine learning model quantization or deep learning frameworks, as it requires a technical understanding of diffusion model implementation.

deep-learning image-synthesis model-optimization generative-ai model-deployment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

371

Forks

26

Language

Python

License

MIT

Last pushed

Mar 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Xiuyu-Li/q-diffusion"

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