Using Stable Diffusion with Core ML on Apple Silicon
Run Stable Diffusion locally on your MacBook. No cloud, no API calls.
Why it matters
On-device inference capability unlocks edge deployment for generative AI—critical for privacy-conscious enterprises and developers building offline-first applications on Apple hardware.
The key facts
10 to knowStable Diffusion ported to Core ML framework
Enables inference on Apple Silicon (M1/M2)
Local execution without cloud dependency
December 2022 release (early Core ML + generative AI integration)
Published on Hugging Face blog
Stable Diffusion ported to Core ML for Apple Silicon
On-device inference eliminates API call latency and cloud dependency
Published Dec 1 2022—early deployment window for edge AI
Hugging Face diffusers library integration
Enables developers to ship generative features without server infrastructure
Go to the source
Hugging Face Bloghuggingface.co