import requests
from PIL import Image
from transformers import AutoProcessor
from optimum.intel.openvino import OVModelForVisualCausalLM

model_id = "OpenVINO/Qwen3-VL-8B-Instruct-fp16-ov"
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = OVModelForVisualCausalLM.from_pretrained(model_id, trust_remote_code=True)

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"
image = Image.open(requests.get(url, stream=True).raw)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=100)
generated = outputs[:, inputs.input_ids.shape[1]:]
print(processor.batch_decode(generated, skip_special_tokens=True)[0])

pip install huggingface_hub pillow
pip install -U --pre --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly openvino openvino-tokenizers openvino-genai

import huggingface_hub as hf_hub

model_id = "OpenVINO/Qwen3-VL-8B-Instruct-fp16-ov"
model_path = "Qwen3-VL-8B-Instruct-fp16-ov"

hf_hub.snapshot_download(model_id, local_dir=model_path)

import numpy as np
import openvino as ov
import openvino_genai as ov_genai
import requests
from PIL import Image


def load_image(image_source):
    if isinstance(image_source, str) and image_source.startswith(("http://", "https://")):
        image = Image.open(requests.get(image_source, stream=True).raw)
    else:
        image = Image.open(image_source)
    image_data = np.array(image.convert("RGB"))[None]
    return ov.Tensor(image_data)


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

image_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"
image_tensor = load_image(image_url)
prompt = "Describe this image."

print(pipe.generate(prompt, image=image_tensor, max_new_tokens=100))