BiRefNet-lite 1024 (ONNX, WebGPU-runnable)

BiRefNet-lite at 1024 × 1024 as an fp16 ONNX export whose graph is patched to run on WebGPU in the browser; the weights are unchanged. Card Anvil uses it with Transformers.js to select the main subject of card art.

These are unchanged copies of the files in jiabins0303/birefnet-lite-1024-webgpu at commit 1ad01ce, at the same paths, kept here so the app loads files that can't change under it.

Files	What they are	Loaded by Card Anvil
`config.json`, `preprocessor_config.json`, `onnx/model_fp16.onnx`	The model	Yes
`scripts/patch_split.py`, `scripts/patch_deform.py`, `scripts/verify_patch.py`	The scripts that rewrote the graph to run on WebGPU, and the check that the result matches the original	No, kept for later
`SOURCE_README.md`	The source repo's README: how and why the graph was patched, and how it was verified	No

Credits and licence

Model: BiRefNet by Peng Zheng et al. (ZhengPeng7/BiRefNet_lite), from Bilateral Reference for High-Resolution Dichotomous Image Segmentation (CAAI AIR 2024).
WebGPU-runnable export: jiabins0303/birefnet-lite-1024-webgpu.

Licensed under the MIT License, as the original model is. See LICENSE.

Loading…

CardAnvilModels/BiRefNet-lite-1024-WebGPU

BiRefNet-lite 1024 (ONNX, WebGPU-runnable)

Credits and licence

BiRefNet-lite 1024 (ONNX, WebGPU-runnable)

Credits and licence