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.
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
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.
