---
title: Spatial-VU
canonical_url: "https://www.modelscope.cn/models/RealmSky/Spatial-VU"
md_url: "https://www.modelscope.cn/models/RealmSky/Spatial-VU.md"
repository: RealmSky/Spatial-VU
last_updated: 2025-10-20
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen2_5_vl
architectures:
  - Qwen2_5_VLForConditionalGeneration
base_model:
  - Qwen/Qwen2.5-VL-7B-Instruct
base_model_relation: finetune
parameters: 8.3B
tensor_type:
  - BF16
library_name:
  - transformer
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 22
stars: 0
tags:
  - text-generation-inference
  - trl
  - spatial-reasoning
  - vision-understanding
---

# Spatial-VU

> Spatial-VU - RealmSky 在 ModelScope 开源的模型。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…

RealmSky/Spatial-VU 是 ModelScope 魔搭社区上的 8.3B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 Qwen/Qwen2.5-VL-7B-Instruct 构建，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: RealmSky/Spatial-VU
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 8.3B
- **Base model**: Qwen/Qwen2.5-VL-7B-Instruct
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: text-generation-inference, trl, spatial-reasoning, vision-understanding
- **Downloads**: 22
- **Stars**: 0
- **Last updated**: 2025-10-20

Source: https://www.modelscope.cn/models/RealmSky/Spatial-VU

---

![1](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/YXaCBzf9LWlg3XEGybIkU.png)

# **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

```python
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.