explainingai-code/DDPM-Pytorch
This repo implements Denoising Diffusion Probabilistic Models (DDPM) in Pytorch
Implements the complete DDPM pipeline with a custom U-Net architecture designed to mirror the stable diffusion model from Hugging Face's diffusers library. Supports training on custom image datasets (MNIST or user-provided PNG files) with configurable model parameters via YAML, and generates image samples across all diffusion timesteps. Includes educational video explanations of both the mathematical foundations and implementation details.
179 stars. No commits in the last 6 months.
Stars
179
Forks
43
Language
Python
License
MIT
Category
Last pushed
Nov 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/explainingai-code/DDPM-Pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
quantgirluk/aleatory
📦 Python library for Stochastic Processes Simulation and Visualisation
TuftsBCB/RegDiffusion
Diffusion model for gene regulatory network inference.
blei-lab/treeffuser
Treeffuser is an easy-to-use package for probabilistic prediction and probabilistic regression...
yuanchenyang/smalldiffusion
Simple and readable code for training and sampling from diffusion models
NVlabs/FastGen
NVIDIA FastGen: Fast Generation from Diffusion Models