# openai/guided-diffusion

Repository: https://github.com/openai/guided-diffusion
Canonical: https://ross.abutalabs.com/products/guided-diffusion
Language: Python
License: MIT
License Family: permissive
Last push: 2024-07-02T11:26:50+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": 1954, "days_push": 792, "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 7419, forks 914 (observed 2026-08-28T04:09:59.771989+00:00)

## What it is
OpenAI's codebase for guided diffusion models from the paper 'Diffusion Models Beat GANs on Image Synthesis', including classifier conditioning and architecture improvements. It provides training code and pre-trained checkpoints for class-conditional and unconditional image generation at multiple resolutions.

## Use cases
- generate images with diffusion models
- train a class-conditional diffusion model
- sample from pretrained ImageNet diffusion checkpoints
- upsample low-resolution images with a diffusion upsampler
- reproduce results from the guided diffusion paper
- experiment with classifier-guided image synthesis

## When to choose
- you want to train or fine-tune diffusion models for image synthesis
- you need classifier-guided generation with OpenAI's pretrained checkpoints
- you're doing research on diffusion model architectures

## When to avoid
- you need actively maintained code with recent dependency support
- you want a general-purpose image generation tool with a simple API
- you need text-to-image generation rather than class-conditional synthesis

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, machine-learning, image-processing
- platform: python
- tags: diffusion-models, image-synthesis, generative-models, pretrained-models, research-code, gpu

## Member repositories
- openai/guided-diffusion (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:59.771989+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 2026-08-29T17:37:45.775182+00:00, confidence not recorded.
  - readme: https://github.com/openai/guided-diffusion (fetched 2026-08-28T04:09:59.771989+00:00, sha 08a989311cdb)
- Data as of 2026-08-30T08:39:29.467469+00:00.