1from libreyolo import LibreYOLO
2
3m = LibreYOLO("LibreFeyNobgl-matte.pt")
4res = m.predict("product.jpg")
5res[0].matte # (H, W) float alpha in [0, 1]
6res[0].save("cut.png") # transparent-background PNG
Derived from
feyninc/FeyNobg
(
nobg library), Apache-2.0,
Copyright (c) 2026 Feyn Inc. FeyNobg builds on
ZhengPeng7/BiRefNet (MIT,
Copyright (c) 2024 ZhengPeng).
Backbone: Swin Transformer v1, Swin-L tier with stage 3 deepened from 18 to
24 blocks (263M parameters). Training data provenance (upstream): not
disclosed by Feyn Inc.; this repo redistributes the author's released
weights under their Apache-2.0 grant and does not redistribute training data.
State-dict key remapping only (fused qkv, renamed modules, wrapped into the
LibreYOLO v1.0 checkpoint schema). Learned parameters are unchanged. Our fp32
forward matches the upstream released weights with
max_abs_diff == 0
(weights/parity_feynobg.py). See
weights/convert_feynobg_weights.py in the
LibreYOLO source repository.
Apache License 2.0. See the
LICENSE and
NOTICE files.
