add sd-turbo onnx

ORT_CUDA/sd-turbo/engine/clip.ort_cuda.fp16/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1b1d827fb6013c67ac3f349b06d1a159373c2faf5253555e20b14ce2ebaacf
+size 680852028

ORT_CUDA/sd-turbo/engine/unet.ort_cuda.fp16/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf77e0fc1a30bd77cbe86ddefccaadc30e2dc3a667c92418f3811f5417ce2af1
+size 371766

ORT_CUDA/sd-turbo/engine/unet.ort_cuda.fp16/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402069ca12429e3f7b810770a49f0121a3f0f025a38317ebfd4b956d7de1c41e
+size 1732024320

ORT_CUDA/sd-turbo/engine/vae.ort_cuda.fp16/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72b771027dde10c6bb0af1347c9e30b0df54f186f3ff7c688f2b89354bcc7a2
+size 99070385

README.md

@@ -1,3 +1,99 @@
 ---
-license: creativeml-openrail-m
+license: openrail++
+base_model: stabilityai/sd-turbo
+language:
+  - en
+tags:
+  - stable-diffusion
+  - sdxl
+  - onnxruntime
+  - onnx
+  - text-to-image
 ---
+
+
+# Stable Diffusion XL Turbo for ONNX Runtime
+
+## Introduction
+
+This repository hosts the optimized versions of **SD Turbo** to accelerate inference with ONNX Runtime CUDA execution provider.
+
+See the [usage instructions](#usage-example) for how to run the SDXL pipeline with the ONNX files hosted in this repository.
+
+## Model Description
+
+- **Developed by:** Stability AI
+- **Model type:** Diffusion-based text-to-image generative model
+- **License:** [STABILITY AI NON-COMMERCIAL RESEARCH COMMUNITY LICENSE](https://huggingface.co/stabilityai/sd-turbo/blob/main/LICENSE)
+- **Model Description:** This is a conversion of the [SD-Turbo](https://huggingface.co/stabilityai/sd-turbo) model for [ONNX Runtime](https://github.com/microsoft/onnxruntime) inference with CUDA execution provider.
+
+## Performance Comparison
+
+#### Latency
+
+Below is average latency of generating an image of size 512x512 using NVIDIA A100-SXM4-80GB GPU:
+
+| Engine      | Batch Size | Steps | PyTorch 2.1     | ONNX Runtime CUDA |
+|-------------|------------|------ | ----------------|-------------------|
+| Static      | 1          |   1   | 85.3 ms         |  32.9 ms          |
+| Static      | 4          |   1   | 213.8 ms        |  97.5 ms          |
+| Static      | 1          |   4   | 117.4 ms        |  62.5 ms          |
+| Static      | 4          |   4   | 294.3 ms        | 168.3 ms          |
+
+
+Static means the engine is built for the given batch size and image size combination, and CUDA graph is used to speed up.
+
+
+## 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:
+
+0. Install nvidia-docker using these [instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
+
+1. Clone onnxruntime repository.
+```shell
+git clone https://github.com/microsoft/onnxruntime
+cd onnxruntime
+```
+
+2. Download the SDXL ONNX files from this repo
+```shell
+git lfs install
+git clone https://huggingface.co/tlwu/sdxl-turbo-onnxruntime
+```
+
+3. Launch the docker
+```shell
+docker run --rm -it --gpus all -v $PWD:/workspace nvcr.io/nvidia/pytorch:23.10-py3 /bin/bash
+```
+
+4. Build ONNX Runtime from source
+```shell
+export CUDACXX=/usr/local/cuda-12.2/bin/nvcc
+git config --global --add safe.directory '*'
+sh build.sh --config Release  --build_shared_lib --parallel --use_cuda --cuda_version 12.2 \
+            --cuda_home /usr/local/cuda-12.2 --cudnn_home /usr/lib/x86_64-linux-gnu/ --build_wheel --skip_tests \
+            --use_tensorrt --tensorrt_home /usr/src/tensorrt \
+            --cmake_extra_defines onnxruntime_BUILD_UNIT_TESTS=OFF \
+            --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=80 \
+            --allow_running_as_root
+python3 -m pip install build/Linux/Release/dist/onnxruntime_gpu-*-cp310-cp310-linux_x86_64.whl --force-reinstall
+```
+
+If the GPU is not A100, change CMAKE_CUDA_ARCHITECTURES=80 in the command line according to the GPU compute capacity (like 89 for RTX 4090, or 86 for RTX 3090). If your machine has less than 64GB memory, replace --parallel by --parallel 4 --nvcc_threads 1  to avoid out of memory.
+
+5. Install libraries and requirements
+```shell
+python3 -m pip install --upgrade pip
+cd /workspace/onnxruntime/python/tools/transformers/models/stable_diffusion
+python3 -m pip install -r requirements-cuda12.txt
+python3 -m pip install --upgrade polygraphy onnx-graphsurgeon --extra-index-url https://pypi.ngc.nvidia.com
+```
+
+6. Perform ONNX Runtime optimized inference
+```shell
+python3 demo_txt2img.py \
+  "starry night over Golden Gate Bridge by van gogh" \
+  --version sd-turbo   \
+  --work-dir /workspace/sd-turbo-onnxruntime
+```