# zoubohao/DenoisingDiffusionProbabilityModel-ddpm-

This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.

Repository: https://github.com/zoubohao/DenoisingDiffusionProbabilityModel-ddpm-
Canonical: https://ross.abutalabs.com/products/denoisingdiffusionprobabilitymodel-ddpm
Language: Python
License: MIT
License Family: permissive
Topics: ddpm
Last push: 2023-04-24T07:52:06+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1562, "days_push": 1227, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2182, forks 218 (observed 2026-08-28T04:06:23.343333+00:00)

## What it is
A minimal, educational PyTorch implementation of Denoising Diffusion Probabilistic Models (DDPM) that trains a UNet on CIFAR-10. It also includes a variant with classifier-free guidance and links to papers and blogs for learning diffusion models.

## Use cases
- learn how diffusion models work
- simplest ddpm implementation to study
- train a unet on cifar-10
- understand classifier-free guidance
- generate images with a diffusion model
- tutorial for denoising diffusion probabilistic models

## When to choose
- you want a small, readable codebase to learn DDPM internals
- you want to train a toy diffusion model on CIFAR-10
- you need a starting point with classifier-free guidance included

## When to avoid
- you need production-grade, scalable diffusion training
- you want high-resolution or text-to-image generation
- you need a maintained library with extensive features

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, machine-learning, image-processing, tutorials
- platform: python
- tags: ddpm, diffusion-models, unet, cifar-10, classifier-free-guidance, educational-implementation

## Member repositories
- zoubohao/DenoisingDiffusionProbabilityModel-ddpm- (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:23.343333+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:48:40.623591+00:00, confidence not recorded.
  - readme: https://github.com/zoubohao/DenoisingDiffusionProbabilityModel-ddpm- (fetched 2026-08-28T04:06:23.343333+00:00, sha edf58aaf2416)
- Data as of 2026-08-30T08:39:29.467469+00:00.