在 Apple Silicon 上使用 Core ML 執行 Stable Diffusion
Original: Using Stable Diffusion with Core ML on Apple Silicon
In late 2022, Apple and Hugging Face jointly announced that Stable Diffusion had officially gained support for Apple Silicon's Core ML…
Apple 與 Hugging Face 合作推出 Core ML 版的 Stable Diffusion，讓 Mac、iPad 和 iPhone 能直接利用 Apple 類神經引擎（ANE）進行硬體加速。開發者可以使用 Hugging Face 的 diffusers 庫與 Apple 的轉換工具，將 PyTorch 模型轉換為 .mlpackage 格式。此舉大幅降低了在 Apple 裝置上部署生成式 AI 模型的門檻，並顯著提升了圖像生成速度與能源效率。
In late 2022, Apple and Hugging Face jointly announced that Stable Diffusion had officially gained support for Apple Silicon's Core ML framework. This update enables Macs (M1/M2 chip series), iPads, and even iPhones to run Stable Diffusion locally and efficiently, without relying on cloud servers.
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 Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.