Instructions to use tencent/WeVisOne-VL-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/WeVisOne-VL-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="tencent/WeVisOne-VL-4B")
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("tencent/WeVisOne-VL-4B")
model = AutoModelForMultimodalLM.from_pretrained("tencent/WeVisOne-VL-4B", 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 tencent/WeVisOne-VL-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/WeVisOne-VL-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/WeVisOne-VL-4B",
		"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/tencent/WeVisOne-VL-4B

SGLang

How to use tencent/WeVisOne-VL-4B 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 "tencent/WeVisOne-VL-4B" \
    --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": "tencent/WeVisOne-VL-4B",
		"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 "tencent/WeVisOne-VL-4B" \
        --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": "tencent/WeVisOne-VL-4B",
		"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 tencent/WeVisOne-VL-4B with Docker Model Runner:
```
docker model run hf.co/tencent/WeVisOne-VL-4B
```

liangtm commited on 7 days ago

Commit

ded38dd

2 Parent(s): ea0abd4 76c2019

Add links to paper, project page, and citation

Browse files

Files changed (1) hide show

README.md +15 -0

README.md CHANGED Viewed

@@ -15,6 +15,8 @@ tags:
 # 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 9.6M-parameter pixel decoder.
 ## Quick Start
@@ -54,3 +56,16 @@ The release is intended for research in visual grounding, referring localization
 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.

 # WeVisOne-VL: Unified Visual Perception from Objects to Pixels
+**Paper:** [WeVisOne-VL: Unified Visual Perception from Objects to Pixels](https://huggingface.co/papers/2610.31329) | **Project Page:** [WeVisOne-VL](https://tencent.github.io/WeVisOne-VL)
 **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 9.6M-parameter pixel decoder.
 ## Quick Start
 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.
+## Citation
+If WeVisOne-VL is helpful to your work, please consider giving us a ⭐ and citing:
+```bibtex
+@article{liang2026wevisone,
+  title={WeVisOne-VL: Unified Visual Perception from Objects to Pixels},
+  author={Liang, Tianming and Pan, Junyi and Li, Yuxi and Fu, Canmiao and Huang, Zhipeng and Sun, Chong and Li, Chen and Lyu, Jing},
+  journal={arXiv preprint arXiv:2610.31329},
+  year={2026}
+}
+```