Spatial-VU

The Spatial-VU model is a fine-tuned version of Qwen2.5-VL-7B-Instruct, tailored for Spatial Reasoning and Vision Understanding. This variant is designed to generate highly detailed and descriptive captions across a broad range of visual categories, including images with complex, sensitive, or nuanced content—across varying aspect ratios and resolutions.

Key Highlights

• Spatial Reasoning & Vision Understanding: Fine-tuned to provide accurate and descriptive visual interpretations, enabling deeper understanding of spatial relationships, structures, and context.

• High-Fidelity Descriptions: Generates comprehensive captions for general, artistic, technical, abstract, and low-context images.

• Robust Across Aspect Ratios: Capable of accurately captioning images with wide, tall, square, and irregular dimensions.

• Variational Detail Control: Produces outputs with both high-level summaries and fine-grained descriptions as needed.

• Foundation on Qwen2.5-VL Architecture: Leverages the strengths of the Qwen2.5-VL-7B multimodal model for visual reasoning, comprehension, and instruction-following.

• Multilingual Output Capability: Can support multilingual descriptions (English as default), adaptable via prompt engineering.

Quick Start with Transformers

from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Spatial-VU", torch_dtype="auto", device_map="auto"
)

processor = AutoProcessor.from_pretrained("prithivMLmods/Spatial-VU")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image in detail."},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=128)
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)

Intended Use

• Generating detailed and unfiltered image captions for general-purpose or artistic datasets.
• Spatial reasoning and vision understanding research.
• Content moderation research, red-teaming, and generative safety evaluations.
• Enabling descriptive captioning for visual datasets typically excluded from mainstream models.
• Use in creative applications (e.g., storytelling, art generation) that benefit from rich descriptive captions.
• Captioning for non-standard aspect ratios and stylized visual content.

Limitations

• May produce explicit, sensitive, or offensive descriptions depending on image content and prompts.
• Not suitable for deployment in production systems requiring content filtering or moderation.
• Can exhibit variability in caption tone or style depending on input prompt phrasing.
• Accuracy for unfamiliar or synthetic visual styles may vary.