Skip to page content
SAVRN
Search Plan a project

Open-weight model

auraface-v1-tflite

by Eungsang eungsang/auraface-v1-tflite

auraface-v1-tflite is an open-weight model from Eungsang, released under Apache License 2.0. Its published files total 65.7 MB.

On-device TFLite conversion of the glintr100.onnx face recognition model from fal/AuraFace-v1 (Apache-2.0). Only the recognition model is included.

Parameters—
Context—
Weights65.7 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Eungsang, published under apache-2.0, revision ac623dbbf0d4.

On-device TFLite conversion of the glintr100.onnx face recognition model from fal/AuraFace-v1 (Apache-2.0). Only the recognition model is included. The other files bundled in the AuraFace repo (scrfd, 2d106det, 1k3d68, genderage) are InsightFace models under a non-commercial license and are not part of this repository. - Converted ONNX (NCHW) → TFLite (NHWC) with onnx2tf, batch fixed to 1. - Cosine similarity to the original ONNX embedding on aligned real faces: mean 0.998. AuraFace-v1 by fal.ai, licensed under the Apache License 2.0. See LICENSE.

Read Eungsang's full model card

AuraFace-v1 (glintr100) — TFLite, int8 weights

On-device TFLite conversion of the glintr100.onnx face recognition model from fal/AuraFace-v1 (Apache-2.0).

Only the recognition model is included. The other files bundled in the AuraFace repo (scrfd, 2d106det, 1k3d68, genderage) are InsightFace models under a non-commercial license and are not part of this repository.

Modifications

  • Converted ONNX (NCHW) → TFLite (NHWC) with onnx2tf, batch fixed to 1.
  • Dynamic-range quantization: weights int8, activations float32.
  • Cosine similarity to the original ONNX embedding on aligned real faces: mean 0.998.

Usage

  • Input: float32[1, 112, 112, 3], RGB, ArcFace 5-point aligned crop, (pixel - 127.5) / 127.5.
  • Output: float32[1, 512] embedding. Compare L2-normalized embeddings with cosine similarity.

Attribution

AuraFace-v1 by fal.ai, licensed under the Apache License 2.0. See LICENSE.

Identity and Version

Repository
eungsang/auraface-v1-tflite
Publisher
Eungsang
Task
Not stated by the source
Modality
Other
Library
tflite
Parameters
Not stated by the source
Languages
on-device
Revision
ac623dbbf0d4e883203f76a30c365bcc967fed3a
First published
2026-10-08
Last updated
2026-10-08

Files and Weights

4 files, 65.7 MB in total. The weights are 1 file totalling 65.7 MB in tflite.

Weights1 file · 65.7 MB
Documentation2 files · 12.5 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
auraface_v1_glintr100_wi8.tfliteWeights65.7 MB 56c854e363b7
LICENSEDocumentation11.4 KB —
README.mdDocumentation1.1 KB —
.gitattributesRepository1.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
65.7 MB
Download from Eungsang

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

Built From

  • Derived from fal/AuraFace-v1

Memory Requirements

PrecisionWeights in memory
As published65.7 MB

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

Questions About auraface-v1-tflite

Can I use auraface-v1-tflite commercially?

Yes. auraface-v1-tflite is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.