SAVRN
Search Contact SAVRN

Open-weight model · Image segmentation

BiRefNet-matting

by Peng Zheng ZhengPeng7/BiRefNet-matting

Check the main BiRefNet model repo for more info and how to use it: https://huggingface.co/ZhengPeng7/BiRefNet/blob/main/README.md Also check the GitHub repo of BiRefNet for all things you may want: https://github.com/ZhengPeng7/BiRefNet + Many thanks to…

Parameters221M
Context—
Weights884.9 MB
Licensemit
AccessOpen weights
Monthly Downloads21.2k

Runs On

What it takes to serve BiRefNet-matting (221M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.4 GB 0.5 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.2 GB 0.3 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

Model Card

By Peng Zheng, published under mit, revision eccde0a8cbdc.

Check the main BiRefNet model repo for more info and how to use it: https://huggingface.co/ZhengPeng7/BiRefNet/blob/main/README.md Also check the GitHub repo of BiRefNet for all things you may want: https://github.com/ZhengPeng7/BiRefNet + Many thanks to @freepik for their generous support on GPU resources for training this model!

Read Peng Zheng's full model card

Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Peng Zheng 1,4,5,6,  Dehong Gao 2,  Deng-Ping Fan 1*,  Li Liu 3,  Jorma Laaksonen 4,  Wanli Ouyang 5,  Nicu Sebe 6
1 Nankai University  2 Northwestern Polytechnical University  3 National University of Defense Technology  4 Aalto University  5 Shanghai AI Laboratory  6 University of Trento 

This repo holds the official weights of BiRefNet for general matting.

Training Sets:

  • P3M-10k (except TE-P3M-500-NP)
  • TR-humans
  • AM-2k
  • AIM-500
  • Human-2k (synthesized with BG-20k)
  • Distinctions-646 (synthesized with BG-20k)
  • HIM2K
  • PPM-100

Validation Sets:

  • TE-P3M-500-NP

Performance:

Dataset Method Smeasure maxFm meanEm MSE maxEm meanFm wFmeasure adpEm adpFm HCE mBA maxBIoU meanBIoU
TE-P3M-500-NP BiRefNet-matting--epoch_100 .979 .996 .988 .003 .997 .986 .988 .864 .885 .000 .830 .940 .888

Check the main BiRefNet model repo for more info and how to use it:
https://huggingface.co/ZhengPeng7/BiRefNet/blob/main/README.md

Also check the GitHub repo of BiRefNet for all things you may want:
https://github.com/ZhengPeng7/BiRefNet

Acknowledgement:

  • Many thanks to @freepik for their generous support on GPU resources for training this model!

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},
  volume = {3},
  pages = {9150038},
  year={2024}
}

Configuration

Architecture
BiRefNet

Identity and Version

Repository
ZhengPeng7/BiRefNet-matting
Publisher
Peng Zheng
Task
Image segmentation
Modality
Image
Library
birefnet
Parameters
221M parameters
Languages
Not stated by the source
Revision
eccde0a8cbdce7ac5fecfeb06340fe7b949e85d9
First published
2024-10-06
Last updated
2026-08-29

Files and Weights

8 files, 885.0 MB in total. The weights are 1 file totalling 884.9 MB in safetensors.

Weights1 file · 884.9 MB
Configuration4 files · 97.6 KB
Documentation1 file · 4.7 KB
Other1 file · 149 B
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights884.9 MB a9875de5b1e6
BiRefNet_config.pyConfiguration298 B —
birefnet.pyConfiguration92.1 KB —
config.jsonConfiguration413 B —
handler.pyConfiguration4.7 KB —
README.mdDocumentation4.7 KB —
requirements.txtOther149 B —
.gitattributesRepository1.5 KB —

License and Download

License
mit
Access
Open weights, no gate
Download size
884.9 MB
Download from Peng Zheng

Released by Peng Zheng through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published884.9 MB
16-bit0.4 GB
8-bit0.2 GB
4-bit0.1 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About BiRefNet-matting

How much GPU memory does BiRefNet-matting need?

About 0.5 GB at 16-bit and 0.1 GB at 4-bit: the weights (221M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run BiRefNet-matting on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use BiRefNet-matting commercially?

Yes. BiRefNet-matting is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

Similar Models

Model · Image segmentation

BiRefNet

Peng Zheng

This repo is the official implementation of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024). Visit our GitHub repo: https://github.com/ZhengPeng7/BiRefNet for more details -- codes, docs, and model zoo! This repo contains the weights of BiRefNet proposed in our paper, which has achieved the SOTA performance on three tasks (DIS, HRSOD, and COD). Go to my GitHub page for BiRefNet codes and the latest updates: https://github.com/ZhengPeng7/BiRefNet:) + Online Image Inference on Colab: + Online Inference with GUI on Hugging Face with adjustable resolutions: + Inference and evaluation of your given weights: + Many thanks to @Freepik for their generous…

Open weights mit 221M parameters birefnet
View model

Model · Image segmentation

RMBG-2.0

BRIA AI

href="https://huggingface.co/briaai/FIBO" target="blank" rel="noopener" aria-label="Explore FIBO on Hugging Face" style=" src="https://huggingface.co/front/assets/huggingfacelogo-noborder.svg" alt="Hugging Face" width="18" height="18" style="display:block" RMBG v2.0 is our new state-of-the-art background removal model significantly improves RMBG v1.4. The model is designed to effectively separate foreground from background in a range of categories and image types. This model has been trained on a carefully selected dataset, which includes: general stock images, e-commerce, gaming, and advertising content, making it suitable for commercial use cases powering enterprise content creation at…

Access requested at publisher other 221M parameters transformers
View model

Model · Image segmentation

BiRefNet_HR

Peng Zheng

This repo is the official implementation of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024). Visit our GitHub repo: https://github.com/ZhengPeng7/BiRefNet for more details -- codes, docs, and model zoo! This repo contains the weights of BiRefNet proposed in our paper, which has achieved the SOTA performance on three tasks (DIS, HRSOD, and COD). Go to my GitHub page for BiRefNet codes and the latest updates: https://github.com/ZhengPeng7/BiRefNet:) + Online Image Inference on Colab: + Online Inference with GUI on Hugging Face with adjustable resolutions: + Inference and evaluation of your given weights: + Many thanks to @freepik for their generous…

Open weights mit 221M parameters birefnet
View model

Model · Image segmentation

BiRefNet_HR-matting

Peng Zheng

This repo is the official implementation of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024). Visit our GitHub repo: https://github.com/ZhengPeng7/BiRefNet for more details -- codes, docs, and model zoo! This repo contains the weights of BiRefNet proposed in our paper, which has achieved the SOTA performance on three tasks (DIS, HRSOD, and COD). Go to my GitHub page for BiRefNet codes and the latest updates: https://github.com/ZhengPeng7/BiRefNet:) + Online Image Inference on Colab: + Online Inference with GUI on Hugging Face with adjustable resolutions: + Inference and evaluation of your given weights: + Many thanks to @freepik for their generous…

Open weights mit 221M parameters birefnet
View model

Model · Image segmentation

BiRefNet-portrait

Peng Zheng

Check the main BiRefNet model repo for more info and how to use it: https://huggingface.co/ZhengPeng7/BiRefNet/blob/main/README.md Also check the GitHub repo of BiRefNet for all things you may want: https://github.com/ZhengPeng7/BiRefNet + Many thanks to @fal for their generous support on GPU resources for training this BiRefNet for portrait matting.

Open weights mit 221M parameters birefnet
View model

Model · Image segmentation

BiRefNet_dynamic

Peng Zheng

For performance of different epochs, check the evalresults-xxx folder for it on my google drive. This repo is the official implementation of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024). Visit our GitHub repo: https://github.com/ZhengPeng7/BiRefNet for more details -- codes, docs, and model zoo! This repo contains the weights of BiRefNet proposed in our paper, which has achieved the SOTA performance on three tasks (DIS, HRSOD, and COD). Go to my GitHub page for BiRefNet codes and the latest updates: https://github.com/ZhengPeng7/BiRefNet:) + Online Image Inference on Colab: + Online Inference with GUI on Hugging Face with adjustable resolutions: +…

Open weights mit 221M parameters birefnet
View model