metadata
license: openrail++
language:
- en
tags:
- stablediffusion
- openvino
HyperSD 1-step LoRA baked-in model converted to OpenVINO(int8) and weights compressed with NNCF(10GB to 4.4GB).
Original Model : Hyper-SD
You can use this model with FastSD CPU.
To run the model yourself, you can leverage the 🧨 Diffusers library:
- Install the dependencies:
pip install optimum-intel openvino diffusers onnx
- Run the model:
from optimum.intel.openvino.modeling_diffusion import OVStableDiffusionXLPipeline
pipeline = OVStableDiffusionXLPipeline.from_pretrained(
"rupeshs/hyper-sd-sdxl-1-step-openvino-int8",
ov_config={"CACHE_DIR": ""},
)
prompt = "a cute cat,flowers"
images = pipeline(
prompt=prompt,
width=768,
height=768,
num_inference_steps=1,
guidance_scale=1.0,
).images
images[0].save("out_image.png")