Stable Diffusion with KerasCV and OpenVINO

This notebook demonstrates how to run KerasCV Stable Diffusion using OpenVINO. An additional part demonstrates how to run optimization with NNCF to speed up pipeline.

Notebook Contents

This notebook demonstrates how to convert, run and optimize stable diffusion using OpenVINO and NNCF.

Notebook contains the following steps:

Convert Stable Diffusion Pipeline models to OpenVINO
- Convert text encoder
- Convert diffusion model
- Convert decoder
Stable Diffusion Pipeline with OpenVINO
Optimize pipeline with NNCF
Compare results of original and optimized pipelines
Interactive Demo

Installation Instructions

This is a self-contained example that relies solely on its own code.
We recommend running the notebook in a virtual environment. You only need a Jupyter server to start. For details, please refer to Installation Guide.