# apple/ml-stable-diffusion

Stable Diffusion with Core ML on Apple Silicon

Repository: https://github.com/apple/ml-stable-diffusion
Canonical: https://ross.abutalabs.com/products/ml-stable-diffusion
Language: Python
License: MIT
License Family: permissive
Last push: 2025-07-03T18:01:03+00:00

## Health v2 (maintenance only)
Score: 36/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 29, release rhythm 8, longevity 99
- inputs: {"age_days": 1387, "days_push": 426, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 17968, forks 1078 (observed 2026-08-28T04:11:20.616533+00:00)

## What it is
Apple's official tooling for running Stable Diffusion on Apple Silicon using Core ML. It includes a Python package for converting PyTorch models to Core ML format and generating images, plus a Swift package for deploying image generation in iOS/macOS apps.

## Use cases
- convert stable diffusion models to core ml
- generate images locally on apple silicon mac
- add stable diffusion to an ios app
- run text-to-image generation on iphone
- benchmark stable diffusion performance on apple devices
- deploy diffusion models with core ml in xcode projects

## When to choose
- you need on-device stable diffusion on macOS, iPhone, or iPad with Apple silicon
- you want a Swift package to integrate image generation into native Apple apps
- you need to convert Hugging Face diffusers models to Core ML format

## When to avoid
- you target NVIDIA GPUs or Linux servers
- you need training or fine-tuning rather than inference
- your devices are pre-M1 Macs or pre-A14 iPhones

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-inference, image-processing, sdk
- domain: machine-learning, image-processing, apple-ecosystem, deep-learning
- platform: python
- tags: stable-diffusion, core-ml, apple-silicon, text-to-image, diffusers, model-conversion, swift-package, macos, ios, swift, apple-ecosystem

## Member repositories
- apple/ml-stable-diffusion (main) score 36

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:20.616533+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 2026-08-29T17:02:12.246743+00:00, confidence not recorded.
  - readme: https://github.com/apple/ml-stable-diffusion (fetched 2026-08-28T04:11:20.616533+00:00, sha 20fbdfc2ae90)
- Data as of 2026-08-30T08:39:29.467469+00:00.