anokimchen/sd-turbo-openvino-8bit-GPT4vision-calibrated

Crashed on Colab CPU

This model is a quantized version of stabilityai/sd-turbo and is converted to the OpenVINO format. This model was obtained via the nncf-quantization space with optimum-intel.

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 OVStableDiffusionPipeline

model_id = "anokimchen/sd-turbo-openvino-8bit"
model = OVStableDiffusionPipeline.from_pretrained(model_id)