Qwen3-VL-2B-FineTuned-Vision-Assistant

messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": "Describe this scene for a blind person."}
    ]
}]
# Output: "A busy intersection with pedestrians waiting at the corner of a crosswalk.
# Traffic lights control vehicle movement and there are several cars stopped in
# adjacent lanes. Buildings with retail stores line both sides of the street,
# with wide sidewalks leading in multiple directions."