tlwu/stable-diffusion-v1-5-onnxruntime

Stable Diffusion 1.5 for ONNX Runtime CUDA provider

Introduction

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.

The models are generated by Olive with command like the following:

python stable_diffusion.py --provider cuda --optimize

Model Description

• Developed by: Stability AI
• Model type: Diffusion-based text-to-image generative model
• License: The CreativeML OpenRAIL M license
• Model Description: This is a conversion of the runwayml/stable-diffusion-v1-5 model for ONNX Runtime inference with CUDA execution provider.