lucidrains/denoising-diffusion-pytorch

Health v2 · maintenance only

Adoption not part of the score

10707 stars · 1282 forks observed · 2026-10-21

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch implementation of Denoising Diffusion Probabilistic Models (DDPM) for generative image modeling, published on PyPI as denoising_diffusion_pytorch. It provides Unet and GaussianDiffusion components plus a Trainer class for training diffusion models on image folders.

Use cases

• train a diffusion model to generate images
• implement DDPM in pytorch
• learn how denoising diffusion probabilistic models work
• generate images from a folder of training data
• experiment with DDIM sampling and diffusion timesteps
• build a generative image model without GANs

When to choose

• you want a simple, readable PyTorch codebase for training diffusion models on images
• you need a pip-installable DDPM implementation with a built-in Trainer
• you are researching or prototyping diffusion-based generative models

When to avoid

• you need production-grade, feature-complete diffusion tooling like text-to-image pipelines or schedulers
• you work outside PyTorch or need non-image modalities
• you require enterprise support or long-term stability guarantees

Facets

library · maturity active

machine-learning deep-learning image-processing deep-learning machine-learning artificial-intelligence image-processing python diffusion-models generative-models pytorch ddpm score-matching image-generation research-code gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lucidrains/denoising-diffusion-pytorch")