Instructions to use OsGo/WeVisOne-VL-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsGo/WeVisOne-VL-2B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="OsGo/WeVisOne-VL-2B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("OsGo/WeVisOne-VL-2B")
model = AutoModelForMultimodalLM.from_pretrained("OsGo/WeVisOne-VL-2B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OsGo/WeVisOne-VL-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OsGo/WeVisOne-VL-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OsGo/WeVisOne-VL-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/OsGo/WeVisOne-VL-2B

SGLang

How to use OsGo/WeVisOne-VL-2B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OsGo/WeVisOne-VL-2B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OsGo/WeVisOne-VL-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OsGo/WeVisOne-VL-2B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OsGo/WeVisOne-VL-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use OsGo/WeVisOne-VL-2B with Docker Model Runner:
```
docker model run hf.co/OsGo/WeVisOne-VL-2B
```

WeVisOne-VL-2B / README.md

OsGo

Update README.md

4c6efc1 verified about 11 hours ago

preview code

Raw History Blame Contribute Delete

3.18 kB

---
license: apache-2.0
pipeline_tag: image-text-to-text
library_name: transformers
tags:
  - vision-language
  - object-detection
  - referring-expression-comprehension
  - object-counting
  - point-grounding
  - ocr
  - referring-expression-segmentation
  - image-matting
---
> ⚠️ **Mirror / Backup Notice:** This repository is an unmodified backup.
> 
> For the latest updates, issues, and support, please visit the [upstream repository](https://huggingface.co/tencent/WeVisOne-VL-2B).


# WeVisOne-VL: Unified Visual Perception from Objects to Pixels

**WeVisOne-VL** (**We**Chat **Vis**ion All-in-**One**) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception (referring segmentation and promptable alpha matting) through structured next-token prediction and a lightweight 9.5M-parameter pixel decoder.

## Quick Start

Install the inference package from [GitHub](https://github.com/Tencent/WeVisOne-VL), then:

```python
from PIL import Image
from wevisone_vl import WeVisOneVL
model = WeVisOneVL("tencent/WeVisOne-VL-2B", device="auto", dtype="bfloat16")
image = Image.open("example.jpg").convert("RGB")
result = model.predict(image, task="matting", query="person", temperature=0.0)
print(result.response, len(result.masks))
```

## Architecture & Released Revision

The model uses dedicated coordinate tokens (`<0>` ... `<1000>`) to represent normalized bounding boxes and points, returns `None` when a queried target is absent, and emits a special instance token (`<OBJ>`, token ID `152678`) after each predicted box for dense tasks.

The attached `mask_decoder.pt` (9,511,460 parameters) is a required core component that combines:
- A **Visual Feature Adapter** over multi-level Qwen3-VL pre-merging ViT features;
- A **Box-Guided Query Decoder** with 6 deformable cross-attention blocks initialized from the `<OBJ>` hidden state and Fourier-encoded box prior;
- An **Instance-Conditioned Dense Prediction Head** with `FullCanvasAlphaCascadeHead` (refining predictions across S/4, S/2, and S/1 to output full-resolution continuous alpha mattes at stride 1).

## Intended Use

The release is intended for research in visual grounding, referring localization, pointing, counting, OCR localization, referring segmentation, and image matting. It is not intended to make autonomous high-impact decisions or to identify individuals.

## Limitations

- Fine alpha boundaries remain sensitive to image resolution, severe occlusion, complex transparency, and prompt phrasing.
- For inference efficiency, the model directly generates structured outputs without explicit chain-of-thought (CoT) reasoning, and currently targets single-turn image perception (video grids are rejected by the pixel decoder).

## License

Unless otherwise noted, Tencent-authored code in this repository is released under the [Apache License 2.0](LICENSE).

Third-party components retain their original licenses and copyright notices. Please review the corresponding source files before use.

	---
	license: apache-2.0
	pipeline_tag: image-text-to-text
	library_name: transformers
	tags:
	- vision-language
	- object-detection
	- referring-expression-comprehension
	- object-counting
	- point-grounding
	- ocr
	- referring-expression-segmentation
	- image-matting
	---
	> ⚠️ Mirror / Backup Notice: This repository is an unmodified backup.
	>
	> For the latest updates, issues, and support, please visit the [upstream repository](https://huggingface.co/tencent/WeVisOne-VL-2B).


	# WeVisOne-VL: Unified Visual Perception from Objects to Pixels

	WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception (referring segmentation and promptable alpha matting) through structured next-token prediction and a lightweight 9.5M-parameter pixel decoder.

	## Quick Start

	Install the inference package from [GitHub](https://github.com/Tencent/WeVisOne-VL), then:

	```python
	from PIL import Image
	from wevisone_vl import WeVisOneVL

	model = WeVisOneVL("tencent/WeVisOne-VL-2B", device="auto", dtype="bfloat16")
	image = Image.open("example.jpg").convert("RGB")
	result = model.predict(image, task="matting", query="person", temperature=0.0)
	print(result.response, len(result.masks))
	```

	## Architecture & Released Revision

	The model uses dedicated coordinate tokens (`<0>` ... `<1000>`) to represent normalized bounding boxes and points, returns `None` when a queried target is absent, and emits a special instance token (`<OBJ>`, token ID `152678`) after each predicted box for dense tasks.

	The attached `mask_decoder.pt` (9,511,460 parameters) is a required core component that combines:
	- A Visual Feature Adapter over multi-level Qwen3-VL pre-merging ViT features;
	- A Box-Guided Query Decoder with 6 deformable cross-attention blocks initialized from the `<OBJ>` hidden state and Fourier-encoded box prior;
	- An Instance-Conditioned Dense Prediction Head with `FullCanvasAlphaCascadeHead` (refining predictions across S/4, S/2, and S/1 to output full-resolution continuous alpha mattes at stride 1).

	## Intended Use

	The release is intended for research in visual grounding, referring localization, pointing, counting, OCR localization, referring segmentation, and image matting. It is not intended to make autonomous high-impact decisions or to identify individuals.

	## Limitations

	- Fine alpha boundaries remain sensitive to image resolution, severe occlusion, complex transparency, and prompt phrasing.
	- For inference efficiency, the model directly generates structured outputs without explicit chain-of-thought (CoT) reasoning, and currently targets single-turn image perception (video grids are rejected by the pixel decoder).

	## License

	Unless otherwise noted, Tencent-authored code in this repository is released under the [Apache License 2.0](LICENSE).

	Third-party components retain their original licenses and copyright notices. Please review the corresponding source files before use.