Build with InsightFace: face recognition and optional RGB liveness, a self-hosted server, video face privacy with PrivateFrame, face swapping, deepfake detection, and commercial model licensing.
1import insightface2import cv234# Face Recognition5app = insightface.app.FaceAnalysis('buffalo_l')6app.prepare(ctx_id=0)7img = cv2.imread('photo.jpg')8faces = app.get(img)9print(faces[0].embedding.shape)1011# Face Swapping12swapper = insightface.model_zoo.get_model(13 'inswapper_128.onnx')14res = swapper.get(img, faces[0], faces[1])15cv2.imwrite('swapped.jpg', res)Trusted by teams building the next generation of face AI
Solutions
Face recognition, optional RGB liveness, video face privacy, and creative tools for your product. Explore self-hosted services, SDKs, and commercial model licensing.
Commercial licensing for InsightFace open-source model packages (buffalo_l, antelopev2, buffalo_s, buffalo_m, etc.) and proprietary high-accuracy models. From research to production deployment with full legal compliance.
Optionally enable RGB liveness checks before face recognition through the Python package or InsightFace Server.
Keep video face redaction on your own device. Track faces, choose who stays visible, and export blur or mosaic with the desktop app, CLI, or Python.
Commercial model license required
A self-hosted recognition service with optional RGB liveness, Web UI, REST API, Python SDK, CPU or CUDA inference, exact 1:N search, and persistent RTSP monitoring.
Cross-platform C/C++ face recognition SDK with built-in anti-spoofing and liveness detection. Commercial licensing with dedicated technical support for Linux, Android, iOS, macOS, and embedded devices.
Open-source InSwapper-128 has become the de facto standard for open-source face swapping, with commercial licensing, high-accuracy private models, mobile real-time models, and a local NVIDIA GPU real-time solution for professional live streaming.
Enterprise deepfake and face-forgery detection via SDK and API. Try the online demo to identify AI-generated faces, face swaps, and manipulated media with calibrated risk scoring for KYC, content moderation, and trust & safety.
Run authorized real-time AI identity transformation locally on a streamer’s NVIDIA GPU for professional live streaming and virtual production workflows.
Case Studies
From identity verification and access control to creative AI and edge deployment, InsightFace helps teams evaluate, license, and deploy face AI models responsibly.
A fintech team evaluating face recognition models for identity verification, threshold tuning, and production deployment.
An access control provider exploring lightweight face analysis SDK deployment across embedded and edge devices.
A consumer application team reviewing face swap API access, licensing requirements, and responsible use controls.
Anonymized scenarios derived from typical enterprise engagements. Specific customer names are not disclosed for confidentiality reasons.
Licensing & Pricing
From open-source research to model licenses, local live identity deployment, production APIs, and SDK access — choose the licensing option that fits your business needs.
For research and non-commercial projects
Commercial licensing for face recognition and face swapping models
Full suite with API access, SDK, and dedicated support
Integration
Whether you prefer Python, C++, or REST — InsightFace integrates into your stack with minimal friction.
Face analysis in Python, with optional RGB liveness before recognition and per-face results.
Explore RGB livenesspip install insightface onnxruntime-gpu
# That's it. You're ready.
from insightface.app import FaceAnalysis
app = FaceAnalysis('buffalo_l')
app.prepare(ctx_id=0)Native SDK for mobile and embedded devices. One API across all platforms.
// Initialize the SDK
HResult ret = HFLaunchInspireFace(path);
// Create a session
HFSession session;
HFCreateInspireFaceSession(&session, mode);
// Detect and recognize
HFDetectFaces(session, image, &faces);
HFExtractFeature(session, image, face, &feature);Self-host detection, optional RGB liveness, comparison, enrollment, and exact person search on CPU or NVIDIA GPU.
Explore RGB liveness# Authenticated deployment; omit -H when auth is disabled.
curl -sS http://localhost:18097/v1/detect \
-H "Authorization: Bearer ${INSIGHTFACE_API_KEY}" \
-F "image=@photo.jpg"Research & Publications
Published at top-tier academic venues. Every algorithm in InsightFace is peer-reviewed and reproducible.
CVPR 2019
The foundational loss function for face recognition, setting new benchmarks on all major datasets.
CVPR 2020
Practical single-stage face detector with joint face detection and landmark localization.
ICLR 2022
Efficient high-accuracy face detection with NAS-based architecture search.
CVPR 2022
Scalable training strategy enabling face recognition with massive identity pools.
ECCV 2020
Handling noisy training data by learning multiple sub-centers per class.
Achievements
Top Performer on VISA and Wild Tracks
3D Face Reconstruction Challenge
Masked Face Recognition Workshop
InsightFace's code is released under the MIT License with no limitations for commercial usage. Pre-trained models are for non-commercial research only — contact us for commercial model licensing.
View on GitHubBlog
Stay up to date with the latest developments in face AI technology, research, and applications.
A practical August 2026 roundup of one-shot portrait animation at 32 FPS, minute-level joint audio-video avatar streaming, and geometry-guided emotional talking faces with continuous intensity control.
A detailed August 2026 arXiv briefing on the synthetic-to-real gap in low-resolution recognition, identity-preserving face compression below one kilobyte, and a Brazilian fairness benchmark grounded in self-declared race/color records.
August's face detection and capture-security briefing covers runtime-configurable facial landmarks, presentation-attack training without human faces, and a systematic comparison of foundation models for presentation and morph attacks.
Whether you need face recognition model licensing, face swapping commercial rights, a live streaming identity deployment, a local real-time identity workflow, InspireFace SDK, or custom AI cooperation — contact us to start the conversation.
We review commercial, enterprise, and research cooperation requests. Please use a company email address when possible.