BiRefNet-lite 512px ONNX (WASM tier)

Verbatim mirror of studioludens/birefnet-lite-512 (MIT), pinned for the BRPOD print-on-demand decorator's client-side background removal. Fixed 512x512 input; onnx/model_fp16.onnx (94 MB) is what the decorator loads on the WASM backend, onnx/model.onnx (fp32, 183 MB) is kept as a fallback. Output is single-channel logits (transformers.js applies sigmoid).

Upstream weights: ZhengPeng7/BiRefNet_lite (MIT). The ONNX export methodology and files come from the source repo above; nothing was retrained or modified. Both config.json and preprocessor_config.json are byte-identical to the source.

Do not modify this repo in place. Publish changes as new commits and bump the pinned revision in BRPOD's backgroundRemovalService.ts, which loads this repo by commit sha.

Citation

@article{zheng2024birefnet,
  title={Bilateral Reference for High-Resolution Dichotomous Image Segmentation},
  author={Zheng, Peng and Gao, Dehong and Fan, Deng-Ping and Liu, Li and Laaksonen, Jorma and Ouyang, Wanli and Sebe, Nicu},
  journal={CAAI Artificial Intelligence Research},
  year={2024}
}
Downloads last month
33
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for BRPOD123/birefnet-lite-512

Quantized
(11)
this model