LibreFeyNobgl-matte

FeyNobg background removal, repackaged for LibreYOLO's matte task. Predicts a soft alpha matte at a fixed native 1024x1024.

from libreyolo import LibreYOLO

m = LibreYOLO("LibreFeyNobgl-matte.pt")
res = m.predict("product.jpg")
res[0].matte            # (H, W) float alpha in [0, 1]
res[0].save("cut.png")  # transparent-background PNG

Source

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.

Modifications

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.

License

Apache License 2.0. See the LICENSE and NOTICE files.