CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.vision / BiRefNet-portrait
From: ZhengPeng7 <huggingface.co/ZhengPeng7>Newsgroups: alt.freeweights.visionSubject:

BiRefNet-portrait

Date: 2026-11-15Commit: b656196Signed: 2DC28CC7B26A283B ✓

Image segmentation model with 221M parameters. Safetensors weights, 885 MB in all. Published by ZhengPeng7 under MIT.

221M params885MBBiRefNet-portraitsafetensorspermissive
FactsParams221MSize885 MBFormatssafetensorsTaskimage segmentationLicenseMITFrom sourcepermissive
$ fw get ZhengPeng7/BiRefNet-portrait
# manifest sha256 67a6399154a1… · 885 MB · 9 files
$ fw verify ./BiRefNet-portrait ZhengPeng7/BiRefNet-portrait
From sourceHosted (signed)ZhengPeng7/BiRefNet-portraitLast check: 2026-11-15 02:29 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
885 MB
Weights
885 MB (safetensors)
Parameters
221M
Formats
safetensors
Task
image segmentation
License
MIT (permissive)
Files
9, each with a sha256
Publisher
ZhengPeng7
Added
2026-11-15
Section
alt.freeweights.vision
Lineage

Original release from the publisher.

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 02:29 UTCpassed

Model card

From the publisher at commit b656196. Shown as plain text with links; images open at the publisher.

Bilateral Reference for High-Resolution Dichotomous Image Segmentation#

Peng Zheng 1,4,5,6,&thinsp; Dehong Gao 2,&thinsp; Deng-Ping Fan 1*,&thinsp; Li Liu 3,&thinsp; Jorma Laaksonen 4,&thinsp; Wanli Ouyang 5,&thinsp; Nicu Sebe 6

1 Nankai University&ensp; 2 Northwestern Polytechnical University&ensp; 3 National University of Defense Technology&ensp; 4 Aalto University&ensp; 5 Shanghai AI Laboratory&ensp; 6 University of Trento&ensp;

https://arxiv.org/pdf/2401.03407&ensp; https://drive.google.com/file/d/1aBnJ_R9lbnC2dm8dqD0-pzP2Cu-U1Xpt/view?usp=drive_link&ensp; https://www.birefnet.top&ensp; https://drive.google.com/drive/folders/1s2Xe0cjq-2ctnJBR24563yMSCOu4CcxM&ensp; LICENSE&ensp; https://huggingface.co/spaces/ZhengPeng7/BiRefNet_demo&ensp; https://huggingface.co/ZhengPeng7/BiRefNet&ensp; https://colab.research.google.com/drive/14Dqg7oeBkFEtchaHLNpig2BcdkZEogba?usp=drive_link&ensp; https://colab.research.google.com/drive/1MaEiBfJ4xIaZZn0DqKrhydHB8X97hNXl#scrollTo=DJ4meUYjia6S&ensp;

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

Training Sets:#
Validation Sets:#
  • TE-P3M-500-P
Performance:#
DatasetMethodSmeasuremaxFmmeanEmMAEmaxEmmeanFmwFmeasureadpEmadpFmHCE
TE-P3M-500-PBiRefNet-portrai--epoch_150.983.996.991.006.997.988.990.933.965.000

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 @fal for their generous support on GPU resources for training this BiRefNet for portrait matting.

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}
}

Files

9 files · 885 MBWeights 885 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
.gitignore1.91 KB32c2a6d082cb35dcec4af9517742b093e3d4fa7e27208fc0d0cbbdfed859bf19
BiRefNet_config.py298 Be7b8c2a74f6cea6a59553d517f71d47f2c1d90e670a13416af17c25fe2f3dc52
README.md4.58 KB3704c67a4bec59d8af983caf1711905ec71548a23c2b4455eac13be5c4336e2a
birefnet.py92.1 KB2a45b4e0ece72d7c4212bca1a988e7d7e52bfe9f98ec59c58b8809c8a8b7a831
config.json414 B68a27b9f0058e0d81f8b32655c3b5b8d82838c523243a2851b8269dd3f080a0e
handler.py4.71 KB2bc2fa0050b600ed8dcaa9403ed41f118a9d9657bf61ca018e03b16f6aab0b9b
model.safetensors885 MB4a4eb3a5469b75f0cccaec6772c22fc30e6c12ed429c2c0ba71b43e3d8d97182
requirements.txt149 Bbdfdd83a090d31a2acf64f7350653fa63cd8b5d9d6e0ff3e135bea7ce3786341
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
b6561965a7 pinned now2026-11-15 02:29 UTC9 files · 885 MB

Use it

$ fw get ZhengPeng7/BiRefNet-portrait
# manifest sha256 67a6399154a1… · 885 MB · 9 files
$ fw verify ./BiRefNet-portrait ZhengPeng7/BiRefNet-portrait
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/ZhengPeng7/BiRefNet-portrait.json --dir ./BiRefNet-portrait $ python3 fw.py verify ./BiRefNet-portrait ./ZhengPeng7__BiRefNet-portrait.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ZhengPeng7/BiRefNet-portrait --revision b6561965a70070d9143fd9e558f6ca3c481510db --local-dir ./BiRefNet-portrait
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
3704c67a4bec59d8af983caf1711905ec71548a23c2b4455eac13be5c4336e2a
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: ZhengPeng7 <huggingface.co/ZhengPeng7>Newsgroups: alt.freeweights.visionSubject: BiRefNet-portraitDate: 2026-11-15Commit: b656196Signed: 2DC28CC7B26A283B ✓
Upstream
ZhengPeng7/BiRefNet-portrait
Pinned commit
b6561965a70070d9143fd9e558f6ca3c481510db
Manifest
BiRefNet-portrait.json · .minisig
Manifest sha256
67a6399154a1406ec5eae25c1ad3a1e704b79915191037dca9545e88856f5dfa
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:29 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ZhengPeng7/BiRefNet-portrait.json $ curl -O https://freeweights.allternit.com/manifests/ZhengPeng7/BiRefNet-portrait.json.minisig $ minisign -Vm BiRefNet-portrait.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

1 model in the catalog name this one as their parent.

Quantizations
1
Quantizations 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ZhengPeng7/BiRefNet-portrait
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. BiRefNet-portrait.json. Provenance. Takedown history: none.
Source
huggingface.co/ZhengPeng7/BiRefNet-portrait

Variants

1 quantized or adapter build of BiRefNet-portrait. Each has its own license check and page.

SubjectSizeParamsLicenseDate
BiRefNet-portrait-ONNXHosted (signed) From: onnx-community in alt.freeweights.vision1.46 GB—Permissive2026-11-15

Related models

All of alt.freeweights.vision →
From: dima806 <huggingface.co/dima806>Subject: ai_vs_real_image_detection
From: legekka <huggingface.co/legekka>Subject: AI-Anime-Image-Detector-ViT
From: onnx-community <huggingface.co/onnx-community>Subject: AI-Anime-Image-Detector-ViT-ONNX
From: AICodexLab <huggingface.co/AICodexLab>Subject: answerdotai-ModernBERT-base-ai-detector
From: onnx-community <huggingface.co/onnx-community>Subject: answerdotai-ModernBERT-base-ai-detector-ONNX
From: onnx-community <huggingface.co/onnx-community>Subject: bart-large-cnn-ONNX