Tencent releases WeVisOne-VL-4B unified visual perception model
Tencent WeChat Vision released WeVisOne-VL-4B, a Qwen3-VL-based vision-language model designed to combine object-level perception with pixel-level tasks. Tencent’s model card lists open-vocabulary object detection, referring localization, object counting, object pointing, OCR localization, referring segmentation, and promptable alpha matting. The release includes an inference package and a required 9.6-million-parameter pixel decoder. Tencent says fine alpha boundaries are sensitive to image resolution, severe occlusion, complex transparency, and prompt phrasing, and that the model currently targets single-turn image perception. Unless otherwise noted, Tencent-authored code is released under Apache License 2.0; third-party components retain their original licenses and copyright notices.
The release provides a research-oriented model, inference package, and pixel-decoder implementation that combine visual grounding and localization with dense prediction and promptable alpha matting. Its listed capabilities and limitations come from Tencent’s model card and have not been independently verified in the supplied report.
tencent/WeVisOne-VL-4B Image-Text-to-Text • 5B • Updated 4 days ago • 8.11k • 89
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
WeVisOne-VL: Unified Visual Perception from Objects to Pixels
Paper: WeVisOne-VL: Unified Visual Perception from Objects to Pixels | Project Page: WeVisOne-VL
#Tencent#WeChat Vision#WeVisOne-VL-4B#Qwen3-VL#Apache-2.0#Transformers