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).
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.
Stars
54
Forks
8
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
xie-lab-ml/Golden-Noise-for-Diffusion-Models
[ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".
yulewang97/ERDiff
[NeurIPS 2023 Spotlight] Official Repo for "Extraction and Recovery of Dpatio-temporal Structure...
UNIC-Lab/RadioDiff
This is the code for the paper "RadioDiff: An Effective Generative Diffusion Model for...
zju-pi/diff-sampler
An open-source toolbox for fast sampling of diffusion models. Official implementations of our...
dome272/Paella
Official Implementation of Paella https://arxiv.org/abs/2211.07292v2