Ready in ~10 minutes (after Drive download):

1. Put runtime under lib\cpu\ → 2) pip install -r requirements.txt → 3) run.bat → 4) Postman or run_demo.bat.
   Jump: Download runtime · Start the API · About SDK

FacePlugin Face Liveness SDK detects presentation attacks (photo, screen, print, replay) from a single RGB face image.

This repository is standalone. Download the runtime into this repo and run — no other FacePlugin repository is required.

This is an on-premise FacePlugin SDK. All processing stays on your machine — no biometric data is sent to FacePlugin cloud.

Windows product: native x64 runtime + local HTTP API and Gradio demo. (No Docker on Windows — use FaceLiveness-Linux-App for Docker.)

API server — test with Postman, curl, or the local Gradio demo (demo.py).

Score ≥ 0.5 → result: "Real", pass: true. Score < 0.5 → result: "Spoof", pass: false.

You do not need a license to start the API once. Product endpoints unlock after you activate.

The ./lib/cpu/ tree is intentionally empty on GitHub because native binaries and model files are too large.

FaceLiveness-Windows-App runtime (Google Drive)

Download library files into ./lib/cpu/.

The Windows product is CPU-only — there is no gpu\ package.

1. Clone the repo (if you have not already):

git clone https://github.com/Faceplugin-ltd/FaceLivenessDetection-Windows.git
cd FaceLivenessDetection-Windows

2. Open the Google Drive folder above.
3. Download all files in that folder (Drive: select all → Download, or download as a zip).
4. Put every file directly into .\lib\cpu\ — not inside a nested subfolder.

Correct layout:

FaceLivenessDetection-Windows/
└── lib/
    └── cpu/
        ├── FaceLivenessSDK.dll
        ├── fal-eng.dll
        ├── fal.fpk
        └── ... (VC++ redist and other runtimes from Drive)

Wrong layout: lib\cpu\SomeFolder\FaceLivenessSDK.dll (a nested folder breaks local runs).

5. Quick check:

dir lib\cpu\FaceLivenessSDK.dll
dir lib\cpu\fal-eng.dll
dir lib\cpu\fal.fpk

If those paths exist, you are ready to start.

The VC++ runtime DLLs ship inside lib\cpu\. You do not install vcredist. run.bat puts that folder on PATH.

You can start without a license — the server prints your machine code on startup.

pip install -r requirements.txt
run.bat

API: http://127.0.0.1:8084

The API starts even if activation fails. Copy the machine code (FPMC1.…) from the log and send it to FacePlugin. When prompted, paste your FP1. license key (or skip and activate later).

Licenses are offline and bound to your machine. Offline cryptography is pre-packaged within the SDK—no third-party licensing libraries or external OpenSSL installations are required.

1. Start the server (above). A license is not required for the first start.
2. Copy the machine code from the terminal. It looks like FPMC1.….
3. Send that machine code to FacePlugin (contact). We will issue a license key for that code.
4. Activate with the license key — either paste it when run.bat prompts you (see screenshot above), or:

:: After run run.bat, paste the FP1. key on terminal like top screenshot. This is the easiest way and you can try 3 times.

:: Paste the FP1. key into .\license.txt (overwrite the file), then:

curl -s -X POST http://127.0.0.1:8084/api/activate -H "Content-Type: text/plain" --data-binary @license.txt

:: Or stop the process (Ctrl+C), save license.txt, and run run.bat again

curl -s http://127.0.0.1:8084/api/health

curl -s -X POST http://127.0.0.1:8084/api/liveness -H "Content-Type: application/json" -d "{\"image\":\"<base64-jpeg>\"}"

Success data:

{ "score": 0.72, "result": "Real", "pass": true }

https://doc.faceplugin.com

Import postman/FaceLiveness-API.postman_collection.json.

Default base URL: http://127.0.0.1:8084

Canonical protocol: /api/* (see FacePlugin Protocol). No version segment in route paths.

For a simple browser test UI (API must already be running on port 8084):

pip install -r requirements-demo.txt
run_demo.bat

Or (CMD):

set DEMO_PORT=9004
set API_BASE=http://127.0.0.1:8084
python demo.py

PowerShell:

$env:DEMO_PORT = "9004"
$env:API_BASE = "http://127.0.0.1:8084"
python demo.py

Open http://127.0.0.1:9004. Samples: assets/examples/samples/.

Each run shows Score, Result (Real or Spoof), and Pass.

Use the Python bindings in sdk.py. Return code 0 means success.

import sdk

machine_code = sdk.get_machine_code()  # FPMC1.…
sdk.activate("license.txt")
sdk.init_sdk()
result = sdk.liveness(base64_image)

result is JSON. data is { "score": <float>, "result": "Real" | "Spoof", "pass": <bool> }. All RGB engines are always run and combined.

HTTP endpoints: /api/health, /api/machinecode, /api/backend, /api/activate, /api/liveness, /api/check_liveness.

• Face Recognition with Liveness Detection-Android (Java, Kotlin)
• Face Recognition with Liveness Detection-iOS (Objective C, Swift)
• Face Recognition with Liveness Detection-Windows
• Face Recognition with Liveness Detection-React Native
• Face Recognition with Liveness Detection-Flutter
• Face Recognition with Liveness Detection-Ionic Cordova
• Face Recognition with Liveness Detection-.Net MAUI
• Face Recognition with Liveness Detection-.Net WPF
• Face Recognition with Liveness Detection-Javascript
• Face Recognition with LivenessDetection-React
• Face Recognition with LivenessDetection-Vue
• Face Liveness Detection-Android (Java, Kotlin)
• Face Liveness Detection-iOS (Objective C, Swift)
• Face Liveness Detection-Windows
• Face Liveness Detection-Linux
• Face Liveness Detection-Docker
• Open Source Face Recognition SDK
• Face Recognition SDK
• Liveness Detection SDK
• Palm Recognition SDK
• ID Document Recognition-Android (Java, Kotlin)
• ID Document Recognition-Windows
• ID Document Recognition
• ID Document Liveness Detection