u2netp.onnx: background segmentation model used by the Known Quantity photo editor (/tools/photo-editor/). It runs in the visitor's browser; no photo is sent anywhere. Model: U^2-Net, small version (u2netp), by Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R. Zaiane and Martin Jagersand, "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection", Pattern Recognition 106, 2020. https://github.com/xuebinqin/U-2-Net Licensed under the Apache License, Version 2.0 (see LICENSE.txt in this folder). ONNX export: the rembg project by Daniel Gatis (MIT License, see LICENSE-rembg.txt), release asset https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2netp.onnx sha256 309c8469258dda742793dce0ebea8e6dd393174f89934733ecc8b14c76f4ddd8 (4,574,861 bytes; the file here is that asset, unmodified). Runtime: ONNX Runtime Web by Microsoft (MIT License), in ../ort/ with its LICENSE.txt, ThirdPartyNotices.txt and VERSION.