No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from tencent/WeVisOne-VL-4B
All models by tencent →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 9.6M-parameter pixel decoder.
Install the inference package from GitHub, then:
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 (9,609,764 parameters) is a required core component that combines:
<OBJ> hidden state and Fourier-encoded box prior;FullCanvasAlphaCascadeHead (refining predictions across S/4, S/2, and S/1 to output full-resolution continuous alpha mattes at stride 1).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.
Unless otherwise noted, Tencent-authored code in this repository is released under the Apache License 2.0 [blocked].
Third-party components retain their original licenses and copyright notices. Please review the corresponding source files before use.
from PIL import Imagefrom wevisone_vl import WeVisOneVL
model = WeVisOneVL("tencent/WeVisOne-VL-4B", 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))