EffectPop background removal

MODNet portrait matting model
Copyright the MODNet authors. Licensed under Apache License 2.0.
Upstream source and model license: https://github.com/ZHKKKe/MODNet#license
Quantized ONNX conversion: https://huggingface.co/Xenova/modnet
Conversion revision: fa2fa546052fba4c08921230a26cc69a333fca12
Original file: onnx/model_quantized.onnx
Distributed file: modnet-quantized-fa2fa54.onnx
SHA-256: 92e49898c3e05a6d7a944fc67a8cb87c4aad754ffb6ebd949528c7d1105fee3a
EffectPop hosts the conversion bytes unchanged under a versioned name.
The quantized conversion is a derivative of the original MODNet model.
Full license: LICENSE-MODNet.txt

Citation
Zhanghan Ke, Jiayu Sun, Kaican Li, Qiong Yan, and Rynson W.H. Lau.
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition.
AAAI 2022. https://arxiv.org/abs/2011.11961

U2NETP general foreground segmentation model
Copyright the U-2-Net authors. Licensed under Apache License 2.0.
Source, original model and license: https://github.com/xuebinqin/U-2-Net
Author confirmation on the released model licenses: https://github.com/xuebinqin/U-2-Net/issues/208
ONNX conversion distributed by rembg (MIT; copyright Daniel Gatis):
https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2netp.onnx
Release asset ID: 85857953
Distributed file: u2netp-309c8469.onnx (4,574,861 bytes)
SHA-256: 309c8469258dda742793dce0ebea8e6dd393174f89934733ecc8b14c76f4ddd8
MD5 published by rembg: 8e83ca70e441ab06c318d82300c84806
EffectPop distributes the released ONNX bytes unchanged and includes no training images.
Full license texts: LICENSE-U2NETP.txt and LICENSE-rembg.txt

Citation
Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R. Zaiane,
and Martin Jagersand. U2-Net: Going Deeper with Nested U-Structure for Salient
Object Detection. Pattern Recognition, 106, 107404, 2020.
https://arxiv.org/abs/2005.09007

ONNX Runtime Web 1.22.0
Copyright (c) Microsoft Corporation. Licensed under the MIT License.
Source: https://github.com/microsoft/onnxruntime/tree/v1.22.0
Package: https://www.npmjs.com/package/onnxruntime-web/v/1.22.0
The WASM and JavaScript glue are unchanged files from the matching NPM release.
Their local names include the version to identify the required matching pair.
ort-wasm-simd-threaded-1.22.0.mjs SHA-256:
30dd851d9c00622940500f71ddd2ff8820c5cb65270816080175b958705385a8
ort-wasm-simd-threaded-1.22.0.wasm SHA-256:
71aef04959c5c1b6de461b6538e2058e306610034a85aad2742d0c7fd4533fe4
Full license: LICENSE-ONNX-Runtime.txt
Bundled dependency notices: ThirdPartyNotices-ONNX-Runtime.txt