Add Ryzen NPU to model card.

README.md

@@ -8,9 +8,13 @@ pipeline_tag: text-to-image
 library_name: diffusers
 ---
 
-# stabilityai/stable-diffusion-3-medium - AMD Optimized ONNX
+# stabilityai/stable-diffusion-3-medium - AMD Optimized ONNX and Ryzen(TM) AI NPU
 
-This repository hosts the **AMD Optimized version of Stable Diffusion 3 Medium** created in collaboration with [AMD](https://huggingface.co/amd).
+This repository hosts the **AMD Optimized version of Stable Diffusion 3 Medium** and the **AMD Ryzen™ AI optimized version of SD 3 Medium** created in collaboration with [AMD](https://huggingface.co/amd).
+
+The AMDGPU model is an AMD-optimized ONNX port of the Stable Diffusion 3 Medium model offering [significantly higher inferencing speeds](https://stability.ai/news/stable-diffusion-now-optimized-for-amd-radeon-gpus) compared to the base model on compatible AMD hardware.
+
+The ONNX-ported Ryzen™ AI model is the world’s first Block FP16 model with the UNET and VAE decoder completely in Block FP16. Built for the AMD XDNA™ 2 based NPU, this model combines the accuracy of FP16 with the performance of INT8.
 
 ## Model Description
 Refer to the [Stable Diffusion 3 Medium Model card](https://huggingface.co/stabilityai/stable-diffusion-3-medium) for more details.
@@ -22,8 +26,9 @@ Refer to the [Stable Diffusion 3 Medium Model card](https://huggingface.co/stabi
 
 ## Running
 
-Use Amuse GUI application to run it: https://www.amuse-ai.com/
-use *_io32 version to run with the Amuse application
+GPU: Use Amuse GUI application to run it: https://www.amuse-ai.com/. Use *_io32 version to run with the Amuse application
+
+NPU: On a compatible XDNA(TM) 2 NPU device, Install and Open Amuse GUI, Click on Advanced Mode. Download SD 3 Medium AMDGPU from Model Manager. Click on Image Generation. Change variant to Ryzen AI. Load. 
 
 
 ## Inference Result