update doc
Browse files
README.md
CHANGED
|
@@ -11,13 +11,15 @@ tags:
|
|
| 11 |
- text-to-image
|
| 12 |
---
|
| 13 |
|
| 14 |
-
# Stable Diffusion 1.5 for ONNX Runtime
|
| 15 |
|
| 16 |
## Introduction
|
| 17 |
|
| 18 |
-
This repository hosts the optimized
|
|
|
|
|
|
|
| 19 |
```
|
| 20 |
-
python stable_diffusion.py --provider cuda
|
| 21 |
```
|
| 22 |
|
| 23 |
## Model Description
|
|
|
|
| 11 |
- text-to-image
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# Stable Diffusion 1.5 for ONNX Runtime CUDA provider
|
| 15 |
|
| 16 |
## Introduction
|
| 17 |
|
| 18 |
+
This repository hosts the optimized onnx models of **Stable Diffusion 1.5** to accelerate inference with ONNX Runtime CUDA execution provider on Nvidia GPUs. It cannot run in other execution providers like CPU or DirectML.
|
| 19 |
+
|
| 20 |
+
The models are generated by [Olive](https://github.com/microsoft/Olive/tree/main/examples/stable_diffusion) with command like the following:
|
| 21 |
```
|
| 22 |
+
python stable_diffusion.py --provider cuda --optimize
|
| 23 |
```
|
| 24 |
|
| 25 |
## Model Description
|