echarlaix/sdxl-turbo-openvino-int8

This model is a quantized version of stabilityai/sdxl-turbo and was exported to the OpenVINO format using optimum-intel via the nncf-quantization space.

First make sure you have optimum-intel installed:

pip install optimum[openvino]

To load your model you can do as follows:

from optimum.intel import OVStableDiffusionXLPipeline

model_id = "echarlaix/sdxl-turbo-openvino-int8"
model = OVStableDiffusionXLPipeline.from_pretrained(model_id)