Deepfake detectionFacesComputer vision

Silent-Face-Anti-Spoofing (MiniFASNet)

Practically the only fully open weight set for single-frame face liveness: it tells a live person from a photo, a screen or a mask. It errs in both directions - a person must be able to appeal a rejection.

The last open version came out in Jun 2020. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
MiniVision Technology, China
First release
Jun 2020
Latest release
Jun 2020
Sizes
two models of about 1.8 MB each
License
Commercial use allowedApache 2.0
Running
On your own serverAlso runs without a GPU
Industries
Security, Finance, HR, Public sector
Deploy on your server GitHub

What it does

  • Liveness check when signing in by selfie
  • Protecting an access system from a photo on a phone
  • A check during remote customer identification
  • Filtering out obvious spoof attempts before manual review

Where it is used

Access control systemsBanks and microfinanceHR and time trackingPublic services

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. MiniFASNetV2 (2.7_80x80) и MiniFASNetV1SE (4_0_0_80x80)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Silent-Face-Anti-Spoofing (MiniFASNet) be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Silent-Face-Anti-Spoofing (MiniFASNet) need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Silent-Face-Anti-Spoofing (MiniFASNet) support Russian?

Language does not matter for this model: it does not work with text.

Where can I download Silent-Face-Anti-Spoofing (MiniFASNet) and what does it cost?

The Silent-Face-Anti-Spoofing (MiniFASNet) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

FacesInsightFaceInsightFace (deepinsight) · ChinaNon-commercial only

The most widely used open toolkit for face detection and recognition. Many identity-preserving image generators are built on it. The pretrained weights are non-commercial.

DetailsDeepfake detectionCommunity ForensicsUniversity of Michigan · USACommercial use allowed

A lightweight detector of generated images, trained on 2.7M samples from nearly 5000 different generators. It errs in both directions: the result is a reason for a human to check, not proof.

DetailsDeepfake detectionDeepfakeBenchThe Chinese University of Hong Kong, Shenzhen (SCLBD) · ChinaNon-commercial only

Dozens of open face-swap detectors for video and photo under one codebase with ready weights. A detector errs in both directions: its output is a reason for a human to check, not proof of a forgery.

Details

Source: github.com/minivision-ai/Silent-Face-Anti-Spoofing. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.