dome272/Diffusion-Models-pytorch resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1458 stars · 307 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A minimal PyTorch implementation of DDPM diffusion models in under 100 lines of code, with conditional and unconditional variants including Classifier-Free Guidance and EMA. It is primarily an educational resource accompanied by explanation videos.

Use cases

• learn how diffusion models work
• implement ddpm from scratch in pytorch
• train a diffusion model on my own images
• generate images with a diffusion model
• understand classifier-free guidance
• follow along with a diffusion models tutorial

When to choose

• you want a short, readable implementation that follows the DDPM paper's Algorithm 1
• you are learning diffusion model theory and want code to match
• you need a starting point to train a small image diffusion model

When to avoid

• you need production-grade training with efficient logging and performance
• you want state-of-the-art diffusion features like latent diffusion or advanced schedulers
• you need a maintained library with stable APIs and releases

Facets

learning-resource · maturity maintenance

machine-learning deep-learning image-processing deep-learning machine-learning artificial-intelligence tutorials python diffusion-models ddpm pytorch image-generation educational classifier-free-guidance gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="dome272/Diffusion-Models-pytorch")