# huggingface/swift-coreml-diffusers

Swift app demonstrating Core ML Stable Diffusion

Repository: https://github.com/huggingface/swift-coreml-diffusers
Canonical: https://ross.abutalabs.com/products/swift-coreml-diffusers
Language: Swift
License: Apache-2.0
License Family: permissive
Last push: 2025-11-06T14:54:04+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 50, release rhythm 35, longevity 97
- inputs: {"age_days": 1359, "days_push": 300, "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 2756, forks 237 (observed 2026-08-28T04:07:18.201796+00:00)

## What it is
A native SwiftUI application demonstrating how to run Stable Diffusion text-to-image generation on-device using Apple's Core ML Stable Diffusion implementation. It serves as both a working app (available on the Mac App Store) and sample code for integrating Core ML diffusers into Swift apps on macOS and iOS.

## Use cases
- generate images from text prompts locally on a Mac or iPhone
- run Stable Diffusion on-device without a server or GPU cloud
- learn how to integrate Core ML Stable Diffusion into a Swift app
- benchmark Stable Diffusion performance on Apple Silicon and Neural Engine
- use quantized Core ML diffusion models on iOS 17 or macOS 14
- build a native iOS text-to-image app with Swift

## When to choose
- you want fully local Stable Diffusion inference on Apple hardware
- you need sample Swift code for Core ML diffusion model integration
- you target macOS or iOS/iPadOS with Apple Silicon or Neural Engine acceleration

## When to avoid
- you need server-side or cross-platform (non-Apple) diffusion inference
- you want training or fine-tuning of diffusion models
- you need the latest model support beyond what Core ML conversion provides
- your devices run macOS 13 or iOS 16 without quantized model support

## Facets
- artifact type: application
- maturity: active
- function: image-processing, machine-learning, llm-inference, sdk
- domain: image-processing, artificial-intelligence, apple-ecosystem, deep-learning
- platform: -
- tags: stable-diffusion, core-ml, swiftui, text-to-image, diffusers, neural-engine, sample-app, macos, ios, swift, apple-ecosystem

## Member repositories
- huggingface/swift-coreml-diffusers (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:18.201796+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 2026-08-30T08:18:51.119903+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/swift-coreml-diffusers (fetched 2026-08-28T04:07:18.201796+00:00, sha c7062461ab9a)
- Data as of 2026-08-30T08:39:29.467469+00:00.