Skip to main content
Qwen3-VL provides precise 2D object grounding capabilities using relative position coordinates. The model supports both bounding boxes and points, enabling diverse combinations of positioning and labeling tasks.

​
Capability Overview

The 2D grounding feature enables you to:
  • Locate objects using bounding boxes
  • Pinpoint specific locations with points
  • Use relative position coordinates
  • Combine multiple grounding formats
  • Perform object detection and localization
  • Support diverse positioning tasks

​
Example Usage

from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained(
    "Qwen/Qwen3-VL-235B-A22B-Instruct", dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-235B-A22B-Instruct")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "path/to/your/image.jpg",
            },
            {"type": "text", "text": "Locate all the objects in this image with bounding boxes."},
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)
inputs = inputs.to(model.device)

generated_ids = model.generate(**inputs, max_new_tokens=512)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

​
Try it Yourself

Explore the full 2D grounding cookbook with interactive examples: Open in Colab View on GitHub