pantheon5100/pid_diffusion

This repository is the official implementation of the paper: Physics Informed Distillation for Diffusion Models, accepted by Transactions on Machine Learning Research (TMLR).

44
/ 100
Emerging

This project helps machine learning engineers create faster image generation models. It takes an existing, powerful diffusion model (the 'teacher') and distills its knowledge into a more efficient 'student' model. The output is a new image generation model that can produce high-quality images much more quickly. This is ideal for developers building applications that require rapid image synthesis.

Use this if you need to speed up the image generation process of an existing diffusion model without significantly sacrificing output quality.

Not ideal if you are looking for a completely new image generation model from scratch or if your primary concern is training time rather than inference speed.

generative AI deep learning optimization image synthesis AI model deployment machine learning engineering
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

54

Forks

8

Language

Python

License

MIT

Last pushed

Nov 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/pantheon5100/pid_diffusion"

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