The SDXL-Lightning model is converted to OpenVINO for fast inference on CPU.

Original Model : SDXL-Lightning

You can use this model with FastSD CPU.

To run the model yourself, you can leverage the 🧨 Diffusers library:

1. Install the dependencies:

pip install optimum-intel openvino diffusers onnx

2. Run the model:

from optimum.intel.openvino.modeling_diffusion import OVStableDiffusionXLPipeline

pipeline = OVStableDiffusionXLPipeline.from_pretrained(
    "rupeshs/SDXL-Lightning-2steps-openvino-int8",
    ov_config={"CACHE_DIR": ""},
)
prompt = "A dolphin leaps through the waves, set against a backdrop of bright blues and teal hues"

images = pipeline(
    prompt=prompt,
    width=768,
    height=768,
    num_inference_steps=2,
    guidance_scale=1.0,
).images
images[0].save("out_image.png")