# ermongroup/ddim

Denoising Diffusion Implicit Models

Repository: https://github.com/ermongroup/ddim
Canonical: https://ross.abutalabs.com/products/ddim
Language: Python
License: MIT
License Family: permissive
Last push: 2024-07-26T09:07:25+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2158, "days_push": 768, "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 1845, forks 231 (observed 2026-08-28T04:05:43.379897+00:00)

## What it is
Official PyTorch implementation of Denoising Diffusion Implicit Models (DDIM), a faster sampling method for diffusion probabilistic models. It also integrates with the Hugging Face Diffusers library via the DDIMPipeline and DDIMScheduler.

## Use cases
- generate images with diffusion models faster
- sample from DDPM models with fewer steps
- train a denoising diffusion model on CIFAR or other datasets
- use DDIM scheduler with Stable Diffusion
- reproduce DDIM paper FID experiments
- accelerate diffusion model inference

## When to choose
- you want faster sampling from diffusion models with fewer steps
- you need the reference implementation of the DDIM paper
- you want a DDIM scheduler for Hugging Face Diffusers pipelines

## When to avoid
- you need a maintained general-purpose diffusion library - use Hugging Face Diffusers instead
- you want production image generation without working with research code
- you need non-PyTorch frameworks

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, llm-inference
- domain: deep-learning, machine-learning, image-processing, artificial-intelligence
- platform: python
- tags: diffusion-models, ddim, ddpm, image-generation, generative-models, sampling, research-code, pytorch, gpu, linux

## Member repositories
- ermongroup/ddim (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:43.379897+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 2026-08-30T03:17:54.921511+00:00, confidence not recorded.
  - readme: https://github.com/ermongroup/ddim (fetched 2026-08-28T04:05:43.379897+00:00, sha 88d9241aafa3)
- Data as of 2026-08-30T08:39:29.467469+00:00.