from optimum.intel.openvino import OVDiffusionPipeline

model_id = "OpenVINO/stable-diffusion-v1-5-fp16-ov"
pipeline = OVDiffusionPipeline.from_pretrained(model_id, safety_checker=None)

prompt = "sailing ship in storm by Rembrandt"
images = pipeline(prompt, num_inference_steps=20).images

Running Model Inference with OpenVINO GenAI

Install packages required for using OpenVINO GenAI.

pip install huggingface_hub
pip install openvino openvino-tokenizers openvino-genai

Download model from HuggingFace Hub

import huggingface_hub as hf_hub

model_id = "OpenVINO/stable-diffusion-v1-5-fp16-ov"
model_path = "stable-diffusion-v1-5-fp16-ov"

hf_hub.snapshot_download(model_id, local_dir=model_path)

Run model inference:

import openvino_genai as ov_genai
from PIL import Image

device = "CPU"
pipe = ov_genai.Text2ImagePipeline(model_path, device)

prompt = "sailing ship in storm by Rembrandt"
image_tensor = pipe.generate(prompt, num_inference_steps=20)
image = Image.fromarray(image_tensor.data[0])

More GenAI usage examples can be found in OpenVINO GenAI library docs and samples

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under creativeml-openrail-m license. More details can be found in stable-diffusion-v1-5/stable-diffusion-v1-5.

Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel’s Global Human Rights Principles. Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.