# Hugging Face — Accelerating Stable Diffusion Inference on Intel CPUs

- Company: Hugging Face (huggingface.co)
- Announced: 2023-03-28
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://huggingface.co/blog/stable-diffusion-inference-intel
- Record: https://forck.live/items/2081-accelerating-stable-diffusion-inference-on-intel-cpus
- Subject: Platform
- Models affected: runwayml/stable-diffusion-v1-5

Techniques to accelerate Stable Diffusion model inference on Intel Sapphire Rapids CPUs using Optimum Intel, OpenVINO, and system-level optimizations, achieving up to nearly 10x speedup compared to previous-generation CPUs.

## Evidence

Verbatim from https://huggingface.co/blog/stable-diffusion-inference-intel:

> Recently, we introduced the latest generation of Intel Xeon CPUs (code name Sapphire Rapids), its new hardware features for deep learning acceleration, and how to use them to accelerate distributed fine-tuning and inference for natural language processing Transformers. In this post, we're going to show you different techniques to accelerate Stable Diffusion models on Sapphire Rapids CPUs.

---

Record: https://forck.live/items/2081-accelerating-stable-diffusion-inference-on-intel-cpus
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md