👁 1.png

Caption3o-XL-2B-Qwen2VL

The Caption3o-XL-2B-Qwen2VL model is a fine-tuned version of Qwen2-VL-2B-Instruct, tailored for Image Captioning and Vision Language Attribution. This variant is designed to generate precise, highly descriptive captions with a focus on defining visual properties, object attributes, and scene details across a wide spectrum of images and aspect ratios.

Key Highlights

1. Vision Language Attribution (VLA): Specially fine-tuned to attribute and define visual properties of objects, scenes, and environments.
2. Detailed Object Definitions: Generates captions with rich attribute descriptions, making outputs more precise than generic captioners.
3. High-Fidelity Descriptions: Handles general, artistic, technical, abstract, and low-context images with descriptive depth.
4. Robust Across Aspect Ratios: Accurately captions images regardless of format—wide, tall, square, or irregular.
5. Variational Detail Control: Supports both concise summaries and fine-grained attributions depending on prompt structure.
6. Foundation on Qwen2-VL Architecture: Leverages Qwen2-VL-2B-Instruct’s multimodal reasoning for visual comprehension and instruction-following.
7. Multilingual Capability: Default in English, but adaptable for multilingual captioning through prompt engineering.

model type: experimental

---

General Query: Caption the image precisely.

---

Demo Inference

---

Quick Start with Transformers

from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2VLForConditionalGeneration.from_pretrained(
 "prithivMLmods/Caption3o-XL-2B-Qwen2VL", torch_dtype="auto", device_map="auto"
)

processor = AutoProcessor.from_pretrained("prithivMLmods/Caption3o-XL-2B-Qwen2VL")

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 with detailed attributes and properties."},
 ],
 }
]

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 attribute-rich image captions for research, dataset creation, and AI training.
• Vision-language attribution for object detection, scene understanding, and dataset annotation.
• Supporting creative, artistic, and technical applications requiring detailed descriptions.
• Captioning across varied aspect ratios, unusual visual styles, and non-standard datasets.

Limitations

• May over-attribute or infer properties not explicitly visible in ambiguous images.
• Outputs can vary in tone depending on prompt phrasing.
• Accuracy may degrade on synthetic or highly abstract visual domains.

Base model

Qwen/Qwen2-VL-2B

Qwen/Qwen2-VL-2B-Instruct

(352)

Multimodal models • 5 items • Updated 2 days ago • 1