Diffusers 正式支援 Stable Diffusion 3：更強大的圖像生成與記憶體優化
Original: Diffusers welcomes Stable Diffusion 3
Hugging Face's official blog announced that its diffusers library now officially supports Stable Diffusion 3 (SD3), the latest release from…
Hugging Face 宣布其 diffusers 函式庫已正式整合 Stability AI 的 Stable Diffusion 3 (SD3)。本次更新全面支援 SD3 Medium 模型，並引入多項關鍵的記憶體優化技術（如 CPU offloading、float16 精度與可選的 T5-XXL 編碼器），讓開發者能在消費級 GPU 上流暢運行。此外，官方也同步釋出了 DreamBooth 與 LoRA 的微調腳本，大幅降低了客製化圖像生成模型的門檻。
Hugging Face's official blog announced that its diffusers library now officially supports Stable Diffusion 3 (SD3), the latest release from Stability AI. SD3 adopts a brand-new Multimodal Diffusion Transformer (MMDiT) architecture, which significantly improves image quality, text rendering capabilities, and comprehension of complex prompts.
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.