rupeshs/LCM-dreamshaper-v7-openvino-int8

Model Descriptions:

This repo contains OpenVino model files for SimianLuo's LCM_Dreamshaper_v7 int8 quantized. This 8 bit model is 1.4x faster than float32 model.

Generation Results:

Usage

You can try out model using Fast SD 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 import OVLatentConsistencyModelPipeline

pipe = OVLatentConsistencyModelPipeline.from_pretrained(
    "rupeshs/LCM-dreamshaper-v7-openvino-int8",
    ov_config={"CACHE_DIR": ""},
)
prompt = "sailing ship in storm by Leonardo da Vinci"
images = pipe(
    prompt=prompt,
    width=512,
    height=512,
    num_inference_steps=4,
    guidance_scale=8.0,
).images
images[0].save("out_image.png")