WeVisOne-VL-2B

A person can use it to analyze images for objects, text, locations, segmentation masks, or alpha mattes.

Availability

Model checkpoint and inference package are publicly linked.

Pricing model

Not stated

Deployment

Local inference using the released model and package.

Privacy

Not established

Licence

Tencent-authored code is under Apache License 2.0; third-party components retain their original licenses.

• The pixel decoder outputs masks and alpha mattes without requiring SAM.
• Model weights, an inference package, cookbooks, and an evaluation pipeline are released.
• A 2B demo is available on Hugging Face Spaces. ^[1]

  - [x] Model weights (2B & 4B) on Hugging Face

• The model supports open-vocabulary object detection, referring localization, counting, pointing, and OCR. ^[2]

  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.

• The model supports referring segmentation and promptable alpha matting. ^[2]

  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.

• The Quick Start loads the model from tencent/WeVisOne-VL-2B and uses the wevisone_vl inference package. ^[2]
• The example initializes the model with device="auto" for inference. ^[2]
• The release is intended for research and is not intended for autonomous high-impact decisions or identifying individuals. ^[2]

  The release is intended for research in visual grounding, referring localization, pointing, counting, OCR localization, referring segmentation, and image matting.

• The model currently targets single-turn image perception, and video grids are rejected by the pixel decoder. ^[2]

  - 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).