update doc

README.md

@@ -14,11 +14,13 @@ tags:
   - text-to-image
 ---
 
-# Stable Diffusion XL Turbo for ONNX Runtime
+# Stable Diffusion XL Turbo for ONNX Runtime CUDA
 
 ## Introduction
 
-This repository hosts the optimized versions of **SDXL Turbo** to accelerate inference with ONNX Runtime CUDA execution provider. The models are generated by [Olive](https://github.com/microsoft/Olive/tree/main/examples/stable_diffusion) with command like the following:
+This repository hosts the optimized onnx models of **SDXL Turbo** to accelerate inference with ONNX Runtime CUDA execution provider for Nvidia GPUs. It cannot run in other providers like CPU or DirectML.
+
+The models are generated by [Olive](https://github.com/microsoft/Olive/tree/main/examples/stable_diffusion) with command like the following:
 ```
 python stable_diffusion_xl.py --provider cuda --model_id stabilityai/sdxl-turbo --optimize --use_fp16_fixed_vae
 ```
@@ -34,26 +36,6 @@ See the [usage instructions](#usage-example) for how to run the SDXL pipeline wi
 
 The VAE decoder is converted from [sdxl-vae-fp16-fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix). There are slight discrepancies between its output and that of the original VAE, but the decoded images should be [close enough for most purposes](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/discussions/7#64c5c0f8e2e5c94bd04eaa80).
 
-The Canny control net is converted from [diffusers/controlnet-canny-sdxl-1.0](https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0).
-
-## Performance Comparison
-
-#### Latency for SDXL-Turbo
-
-Below is average latency of generating an image of size 512x512 using NVIDIA A100-SXM4-80GB GPU:
-
-| Engine      | Batch Size | Steps | PyTorch 2.1 + Diffusers  | ONNX Runtime Demo |
-|-------------|------------|------ | ----------------|-------------------|
-| Static      | 1          |   1   | 109.4 ms        |  49.5 ms          |
-| Static      | 4          |   1   | 247.0 ms        | 143.1 ms          |
-| Static      | 1          |   4   | 171.1 ms        |  104.1 ms         |
-| Static      | 4          |   4   | 390.5 ms        | 271.69 ms         |
-
-
-Static means the engine is built for the given batch size and image size combination, and CUDA graph is used to speed up.
-
-For PyTorch 2.1, the UNet use channel last (NHWC) format, and compile the UNet with mode `reduce-overhead`. See [benchmark script](https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/python/tools/transformers/models/stable_diffusion/benchmark_controlnet.py) for detail.
-
 ## Usage Example
 
 Following the [demo instructions](https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/python/tools/transformers/models/stable_diffusion/README.md#run-demo-with-docker). Example steps: