# hkproj/pytorch-stable-diffusion

Stable Diffusion implemented from scratch in PyTorch

Repository: https://github.com/hkproj/pytorch-stable-diffusion
Canonical: https://ross.abutalabs.com/products/pytorch-stable-diffusion
Homepage: https://www.youtube.com/watch?v=ZBKpAp_6TGI
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: diffusion-models, latent-diffusion-models, paper-implementations, pytorch, pytorch-implementation, stable-diffusion
Last push: 2024-10-22T08:34:36+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 76
- inputs: {"age_days": 1075, "days_push": 680, "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 1078, forks 205 (observed 2026-08-28T04:03:29.811196+00:00)

## What it is
An educational PyTorch implementation of Stable Diffusion built from scratch, provided as Jupyter Notebooks. It is intended for learning how latent diffusion models work rather than for production use.

## Use cases
- learn how stable diffusion works internally
- understand latent diffusion model architecture
- study a from-scratch diffusion model implementation in pytorch
- reimplement stable diffusion for education
- explore the stable diffusion paper code

## When to choose
- you want to understand the internals of stable diffusion
- you are studying diffusion models or paper implementations
- you prefer readable educational code over optimized libraries

## When to avoid
- you need fast, production-ready image generation
- you want fine-tuning or training pipelines with full features
- you need multi-platform support or an API

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, machine-learning, image-processing
- domain: deep-learning, machine-learning, image-processing, tutorials
- platform: python
- tags: stable-diffusion, diffusion-models, pytorch, paper-implementation, educational, jupyter-notebook, gpu

## Member repositories
- hkproj/pytorch-stable-diffusion (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:29.811196+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 2026-08-30T06:53:09.312709+00:00, confidence not recorded.
  - readme: https://github.com/hkproj/pytorch-stable-diffusion (fetched 2026-08-28T04:03:29.811196+00:00, sha 69db1305259b)
  - homepage: https://www.youtube.com/watch?v=ZBKpAp_6TGI (fetched 2026-08-29T12:54:25.800259+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.