Update README.md

README.md

@@ -15,7 +15,9 @@ pipeline_tag: text-to-image
 
 # Small Stable Diffusion Model Card
 【Update 2023/02/07】 Recently, we have released [a diffusion deployment repo](https://github.com/OFA-Sys/diffusion-deploy) to speedup the inference on both GPU (\~4x speedup, based on TensorRT) and CPU (\~12x speedup, based on IntelOpenVINO). 
-Integrated with this repo, small-stable-diffusion could generate images in just **5 seconds on the CPU**.  
+Integrated with this repo, small-stable-diffusion could generate images in just **5 seconds on the CPU**\*.  
+
+*\* Test on Intel(R) Xeon(R) Platinum 8369B CPU, DPMSolverMultistepScheduler 10 steps, fix channel/height/width when converting to Onnx*  
 
 Similar image generation quality, but is nearly 1/2 smaller!  
 Here are some samples:
@@ -26,7 +28,8 @@ Here are some samples:
 
 We support a [Gradio](https://github.com/gradio-app/gradio) Web UI to run small-stable-diffusion-v0:
 [![Open In Spaces](https://camo.githubusercontent.com/00380c35e60d6b04be65d3d94a58332be5cc93779f630bcdfc18ab9a3a7d3388/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d5370616365732d626c7565)](https://huggingface.co/spaces/akhaliq/small-stable-diffusion-v0)
-
+We also provide a space demo for [`small-stable-diffusion-v0 + diffusion-deploy`](https://huggingface.co/spaces/OFA-Sys/FAST-CPU-small-stable-diffusion-v0).   
+*As huggingface provides AMD CPU for the space demo, it costs about 35 seconds to generate an image with 15 steps, which is much slower than the Intel CPU environment as diffusion-deploy is based on Intel's OpenVINO.*
 ## Example
 
 *Use `Diffusers` >=0.8.0, do not support lower versions.*