OPENI BACKGROUND REMOVAL AND REPLACEMENT — THIRD-PARTY NOTICES

This tool's interface, mask editing, compositing, file handling, and integration
were written for Openi. The reference website's implementation is not included.
The following open-source model and inference engine are redistributed locally.

U²-Net / U2NETP — Apache License 2.0
Authors: Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan,
Osmar R. Zaiane, Martin Jagersand.
Project: https://github.com/xuebinqin/U-2-Net
Paper: U²-Net: Going Deeper with Nested U-Structure for Salient Object Detection.
License: /licenses/u2net-apache-2.0.txt
Unmodified ONNX conversion distribution: danielgatis/rembg release v0.0.0
https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2netp.onnx
Model SHA-256: 309c8469258dda742793dce0ebea8e6dd393174f89934733ecc8b14c76f4ddd8
Model MD5 verified against rembg's published download checksum:
8e83ca70e441ab06c318d82300c84806
Rem bg project license: /licenses/rembg-mit.txt (MIT, Copyright Daniel Gatis).
The weights are redistributed without modifications. Input/output processing is
implemented in JavaScript for this tool using the published model convention.

ONNX Runtime Web 1.30.0 — MIT License, Copyright Microsoft Corporation.
Project: https://github.com/microsoft/onnxruntime
License: /licenses/onnxruntime-mit.txt
Upstream third-party notices: /licenses/onnxruntime-third-party.txt
The prebuilt WASM runtime and modules are redistributed without modifications.
Source map comments may refer to development maps, which are not shipped.

All components are provided without warranties; consult the linked full licenses.
No endorsement by these projects is implied.