在 M1 Mac 的 GPU 上本地運行 Stable Diffusion
Original: Run Stable Diffusion on your M1 Mac’s GPU
With the open-sourcing of Stable Diffusion, running powerful AI image generation models locally has become a real possibility. This guide…
本教學指導開發者如何在 M1 Mac 上利用 PyTorch 的 MPS (Metal Performance Shaders) 後端，本地端調用 GPU 運行 Stable Diffusion。內容涵蓋 Python 環境設定、安裝支援 MPS 的 PyTorch 與 Hugging Face diffusers 庫，並提供完整的程式碼範例，讓開發者能完全免費、私密地在 local 端進行 AI 圖像生成與二次開發。
With the open-sourcing of Stable Diffusion, running powerful AI image generation models locally has become a real possibility. This guide published by Replicate explains in detail how to use the GPU in Apple Silicon (M1/M2) chips to deploy and run Stable Diffusion locally on a Mac, freeing developers from dependence on expensive cloud GPU resources while giving them full freedom for secondary development.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Replicate Blog →Summaries are AI-generated; the original article is authoritative.