CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.vision / BiRefNet_dynamic-1024x1024-ONNX
From: onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.visionSubject:

BiRefNet_dynamic-1024x1024-ONNX

Date: 2026-11-15Commit: 6defd3aSigned: 2DC28CC7B26A283B ✓

Image segmentation model. Onnx weights, 1.46 GB in all. Published by onnx-community under MIT.

vision1.46GBBiRefNet_dynamic-1024x1024-ONNXonnxpermissive
FactsParamsnot statedSize1.46 GBFormatsonnxTaskimage segmentationLicenseMITFrom sourcepermissive
$ fw get onnx-community/BiRefNet_dynamic-1024x1024-ONNX
# manifest sha256 1c4199de0952… · 1.46 GB · 6 files
$ fw verify ./BiRefNet_dynamic-1024x1024-ONNX onnx-community/BiRefNet_dynamic-1024x1024-ONNX
From sourceHosted (signed)onnx-community/BiRefNet_dynamic-1024x1024-ONNXLast check: 2026-11-15 05:26 UTC
Run at homeGet help

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

Quantized of BiRefNet_dynamic.

Works with

Run2Convert3Scan1

Runs with

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

UltralyticsOpenVINO

Convert with

ONNXOptimumOlive

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
1.46 GB
Weights
490 MB (smallest of 2 ONNX variants)
Parameters
not stated
Formats
onnx
Task
image segmentation
License
MIT (permissive)
Files
6, each with a sha256
Publisher
onnx-community
Added
2026-11-15
Section
alt.freeweights.vision
Lineage

Original release from the publisher.

Base model: ZhengPeng7/BiRefNet_dynamic

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 05:26 UTCpassed

Model card

From the publisher at commit 6defd3a. 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;

DIS-Sample_1DIS-Sample_2
Image: imageImage: image

For more information, check out the official repository.

Usage (Transformers.js)#

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

You can then use the model for image matting, as follows:

import { AutoModel, AutoProcessor, RawImage } from '@huggingface/transformers';

// Load model and processor
const model_id = 'onnx-community/BiRefNet_dynamic-1024x1024-ONNX';
const model = await AutoModel.from_pretrained(model_id, { dtype: 'fp32' });
const processor = await AutoProcessor.from_pretrained(model_id);

// Load image from URL
const url = 'https://images.pexels.com/photos/5965592/pexels-photo-5965592.jpeg?auto=compress&cs=tinysrgb&w=1024';
const image = await RawImage.fromURL(url);

// Pre-process image
const { pixel_values } = await processor(image);

// Predict alpha matte
const { output_image } = await model({ input_image: pixel_values });

// Save output mask
const mask = await RawImage.fromTensor(output_image[0].sigmoid().mul(255).to('uint8')).resize(image.width, image.height);
mask.save('mask.png');
Input imageOutput mask
Image: image/pngImage: image/png

Citation#

@article{BiRefNet,
  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}
}

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Files

6 files · 1.46 GBWeights 490 MB (smallest of 2 ONNX variants). Sizes and sha256 from the signed manifest.
Hide all 6 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md4.31 KB24a277197a47f68176f3d01fbb7eb74094d1faf3aee1ce02f10abf6bf0202df8
config.json30 B88b20240c9078cf9cc3843dc7d69a42d274b8c242de56a3b2a41ef9995cb93bf
onnx/model.onnx972 MBaa3c17882a27f079fafa7655cf50e83b9e6e067d6c6fa4cbc3524ae441da0bd7
onnx/model_fp16.onnx490 MBee32f829fbf050fd501e53ed330369a71a0cbc69b9ab574da13d18ecbfa93dca
preprocessor_config.json391 B447d9ccb2c4129ab0ca045fc293e7d79dbc45e293ac1e94818d865db77f65a54
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
6defd3a19c pinned now2026-11-15 05:26 UTC6 files · 1.46 GB

Use it

$ fw get onnx-community/BiRefNet_dynamic-1024x1024-ONNX
# manifest sha256 1c4199de0952… · 1.46 GB · 6 files
$ fw verify ./BiRefNet_dynamic-1024x1024-ONNX onnx-community/BiRefNet_dynamic-1024x1024-ONNX
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/onnx-community/BiRefNet_dynamic-1024x1024-ONNX.json --dir ./BiRefNet_dynamic-1024x1024-ONNX $ python3 fw.py verify ./BiRefNet_dynamic-1024x1024-ONNX ./onnx-community__BiRefNet_dynamic-1024x1024-ONNX.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/BiRefNet_dynamic-1024x1024-ONNX --revision 6defd3a19cec21042b178108815c9c4508d09867 --local-dir ./BiRefNet_dynamic-1024x1024-ONNX
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
24a277197a47f68176f3d01fbb7eb74094d1faf3aee1ce02f10abf6bf0202df8
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: onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.visionSubject: BiRefNet_dynamic-1024x1024-ONNXDate: 2026-11-15Commit: 6defd3aSigned: 2DC28CC7B26A283B ✓
Upstream
onnx-community/BiRefNet_dynamic-1024x1024-ONNX
Pinned commit
6defd3a19cec21042b178108815c9c4508d09867
Manifest
BiRefNet_dynamic-1024x1024-ONNX.json · .minisig
Manifest sha256
1c4199de095284fe7c7a9c701ccf5b47027ddd07e6c37662835db52054f71b6b
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:26 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/BiRefNet_dynamic-1024x1024-ONNX.json $ curl -O https://freeweights.allternit.com/manifests/onnx-community/BiRefNet_dynamic-1024x1024-ONNX.json.minisig $ minisign -Vm BiRefNet_dynamic-1024x1024-ONNX.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

Parent

ZhengPeng7/BiRefNet_dynamic · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/BiRefNet_dynamic-1024x1024-ONNX
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. BiRefNet_dynamic-1024x1024-ONNX.json. Provenance. Takedown history: none.
Source
huggingface.co/onnx-community/BiRefNet_dynamic-1024x1024-ONNX

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