---
license: openrail++
base_model: stabilityai/stable-diffusion-xl-base-1.0
language:
  - en
tags:
  - stable-diffusion
  - stable-diffusion-xl
  - tensorrt
  - text-to-image
---

# Stable Diffusion XL 1.0 TensorRT

## Introduction

This repository hosts the TensorRT versions of **Stable Diffusion XL 1.0** created in collaboration with [NVIDIA](https://huggingface.co/nvidia). The optimized versions give substantial improvements in speed and efficiency.


![examples](./examples.jpg)

## Model Description

- **Developed by:** Stability AI
- **Model type:** Diffusion-based text-to-image generative model
- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/LICENSE.md)
- **Model Description:** This is a conversion of the [SDXL base 1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) and [SDXL refiner 1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0) models for [NVIDIA TensorRT](https://developer.nvidia.com/tensorrt) optimized inference


## Performance Comparison

#### Timings for 30 steps at 1024x1024

| Accelerator | Baseline (non-optimized) | NVIDIA TensorRT (optimized) | Percentage improvement |
|-------------|--------------------------|-----------------------------|------------------------|
| A10         | 9399 ms                  | 8160 ms                     | ~13%                   |
| A100        | 3704 ms                  | 2742 ms                     | ~26%                   |
| H100        | 2496 ms                  | 1471 ms                     | ~41%                   |

#### Image throughput for 30 steps at 1024x1024

| Accelerator | Baseline (non-optimized) | NVIDIA TensorRT (optimized) | Percentage improvement |
|-------------|--------------------------|-----------------------------|------------------------|
| A10         | 0.10 images/sec          | 0.12 images/sec             | ~20%                   |
| A100        | 0.27 images/sec          | 0.36 images/sec             | ~33%                   |
| H100        | 0.40 images/sec          | 0.68 images/sec             | ~70%                   |


## Usage Example

1. Following the [setup instructions](https://github.com/rajeevsrao/TensorRT/blob/release/8.6/demo/Diffusion/README.md) on launching a TensorRT NGC container.
```shell
git clone https://github.com/rajeevsrao/TensorRT.git
cd TensorRT
git checkout release/8.6
docker run --rm -it --gpus all -v $PWD:/workspace nvcr.io/nvidia/pytorch:23.06-py3 /bin/bash
```

2. Download the SDXL TensorRT files from this repo
```shell
git lfs install 
git clone https://huggingface.co/stabilityai/stable-diffusion-xl-1.0-tensorrt
cd stable-diffusion-xl-1.0-tensorrt
git lfs pull
cd ..
```

3. Install libraries and requirements
```shell
python3 -m pip install --upgrade pip
python3 -m pip install --upgrade tensorrt

cd demo/Diffusion
pip3 install -r requirements.txt
```

4. Perform TensorRT optimized inference
```
python3 demo_txt2img_xl.py \
  "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" \
  --build-static-batch \
  --use-cuda-graph \
  --num-warmup-runs 1 \
  --width 1024 \
  --height 1024 \
  --denoising-steps 30 \
  --onnx-base-dir /workspace/stable-diffusion-xl-1.0-tensorrt/sdxl-1.0-base \
  --onnx-refiner-dir /workspace/stable-diffusion-xl-1.0-tensorrt/sdxl-1.0-refiner
```