Diffusers 釋出兩個月更新：Stable Diffusion 整合、效能優化與全新 Pipeline
Original: What's new in Diffusers? 🎨
Hugging Face published a major update and progress report on their diffusion model library `diffusers`, two months after its launch. Since…
Hugging Face 發布 Diffusers 開源庫推出兩個月的進展報告。本次更新核心在於全面整合 Stable Diffusion，並推出圖生圖（Img2Img）與局部繪製（Inpainting）等全新 Pipeline。此外，團隊大幅優化了記憶體佔用，引入 Attention Slicing 技術，讓 4GB 顯存的 GPU 也能順利運行擴散模型，並新增了多種採樣調度器（Schedulers）。
Hugging Face published a major update and progress report on their diffusion model library `diffusers`, two months after its launch. Since its release in July 2022, `diffusers` had rapidly become a core tool for the open-source generative AI community, and following the release of Stable Diffusion in August, the library saw explosive growth.
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.