Instructions to use rostrumstudios/birefnet-lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- BiRefNet
How to use rostrumstudios/birefnet-lite with BiRefNet:
# Option 1: use with transformers from transformers import AutoModelForImageSegmentation birefnet = AutoModelForImageSegmentation.from_pretrained("rostrumstudios/birefnet-lite", trust_remote_code=True)# Option 2: use with BiRefNet # Install from https://github.com/ZhengPeng7/BiRefNet from models.birefnet import BiRefNet model = BiRefNet.from_pretrained("rostrumstudios/birefnet-lite") - Notebooks
- Google Colab
- Kaggle
BiRefNet-lite (ONNX), mirrored for Rostrum
BiRefNet-lite (Swin-T backbone), a dichotomous image segmentation model that finds the main subject of a picture, as the fp32 ONNX export by onnx-community (onnx/model.onnx there).
This repository is a pinned, public copy of the exact files the Rostrum apps download. Rostrum fetches each file at a fixed commit of this repository and checks its SHA-256 before use.
What Rostrum uses it for
Design's Select subject: it finds the main subject of a photo and returns a mask. It never draws or changes pixels.
Rostrum uses it for analysis only, never generation: it reads what is in a recording or a picture and makes no new sound, voice or image.
Files
| File | Bytes | SHA-256 |
|---|---|---|
model.onnx |
224,005,088 | 5600024376f572a557870a5eb0afb1e5961636bef4e1e22132025467d0f03333 |
In Rostrum's models folder they go under birefnet-lite/.
Source
| What | Where | Commit / version |
|---|---|---|
| Exact file (unchanged copy of onnx/model.onnx) | https://huggingface.co/onnx-community/BiRefNet_lite-ONNX | de15b22ba131738a16dff04aab8bdf8dc32e3ac1 |
| Original weights | https://huggingface.co/ZhengPeng7/BiRefNet_lite | aa62cd87eafb9cc43056d08ef3615a14628b831d (main when mirrored) |
| Original code | https://github.com/ZhengPeng7/BiRefNet | f7079632d681ecf12161fcea8905682934e59e51 (main when mirrored) |
Authors
Peng Zheng, Dehong Gao, Deng-Ping Fan, Li Liu, Jorma Laaksonen, Wanli Ouyang, Nicu Sebe (BiRefNet); onnx-community (ONNX export).
Licence
MIT (LICENSE, Copyright (c) 2024 ZhengPeng, from the original repository). File redistributed unchanged.
Citation
The original authors ask that you cite:
@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},
volume = {3},
pages = {9150038},
year={2024}
}
Model tree for rostrumstudios/birefnet-lite
Base model
ZhengPeng7/BiRefNet_lite