DeepFace

Spec sheet

What it does

DeepFace is a Python framework for face recognition and facial attribute analysis covering age, gender, emotion and race.Read 21 Oct 2026 · pypi.org

Purpose

DeepFace is a lightweight Python framework for face recognition and facial attribute analysis, including age, gender, emotion, and race.Read 4 Oct 2026 · github.com

Accepted image inputs

The API accepts uploaded files, local paths, URLs and base64-encoded image data.Read 21 Oct 2026 · github.com

Anti-spoofing

Face extraction and streaming can optionally enable anti-spoofing checks to distinguish real faces from spoof inputs.Read 21 Oct 2026 · github.com

API options

DeepFace can be served through REST or gRPC, and its API covers verification, facial attribute analysis, vector representation, registration, and search.Read 4 Oct 2026 · github.com

Attribute analysis

The analyze function predicts age, gender, emotion and race attributes.Read 21 Oct 2026 · deepwiki.com

Database integrations

Database-backed registration and search support PostgreSQL, MongoDB, Weaviate, Neo4j, PGVector and Pinecone, with additional backends listed in the project README.Read 21 Oct 2026 · deepwiki.com

Detection and alignment

Available detector backends include OpenCV, SSD, Dlib, MTCNN, RetinaFace, MediaPipe, YOLO, YuNet, and CenterFace, and alignment can be configured.Read 4 Oct 2026 · github.com

Detector choices

Documented detector backends include OpenCV, SSD, MTCNN, RetinaFace, MediaPipe, YOLO variants, Dlib, YuNet, CenterFace and FastMTCNN.Read 21 Oct 2026 · deepwiki.com

Documentation depth

Independent documentation indexes installation, quick start, core APIs, database integrations, models, REST deployment, Docker, benchmarking and testing.Read 21 Oct 2026 · deepwiki.com

Embeddings

The represent function converts faces into multidimensional embedding vectors.Read 21 Oct 2026 · deepwiki.com

Face search

The find function searches for an input face inside a file-based image database and returns matched identities.Read 21 Oct 2026 · deepwiki.com

Face tasks

Its functions support face verification, finding identities in a folder, image analysis, and producing face embeddings.Read 4 Oct 2026 · github.com

Face verification

The verify function determines whether two supplied face images belong to the same person and returns a verification result with distance information.Read 21 Oct 2026 · github.com

gRPC API

A gRPC service is available with a protobuf contract covering the same core operations as the REST service.Read 21 Oct 2026 · github.com

Hosted API

deepface.dev provides a managed API for verification, embedding generation and vector comparison while handling hosting, scaling and model updates.Read 21 Oct 2026 · deepface.dev

Hosted API authentication

The managed service uses account-created REST or MCP keys and exposes its REST gateway at api.deepface.dev.Read 21 Oct 2026 · docs.deepface.dev

Hosted API endpoints

The managed public API documents POST /verify, POST /represent, POST /compare and GET /capabilities.Read 21 Oct 2026 · docs.deepface.dev

Hosted API request controls

The hosted quickstart documents API keys, model allowlists, optional remote URL fetching checks and an x-request-id for troubleshooting.Read 21 Oct 2026 · docs.deepface.dev

Hosted inputs and access

The hosted API accepts files and base64 by default, provides REST and MCP access, and offers self-serve signup, API keys, usage, and billing.Read 4 Oct 2026 · deepface.dev

Hosted model limits

The hosted service excludes VGG-Face because its released weights are restricted to non-commercial research use and says InsightFace-based ArcFace models require a separate commercial license.Read 4 Oct 2026 · deepface.dev

Install options

The library can be installed from PyPI or source code with TensorFlow, PyTorch, or ONNX Runtime backends.Read 4 Oct 2026 · github.com

Installation

The primary installation method is pip from PyPI, with optional TensorFlow and PyTorch extras and ONNX as the default backend in the current release.Read 21 Oct 2026 · pypi.org

Latest release

PyPI lists DeepFace 0.0.102 as released on October 9, 2026, with one maintainer identified as Sefik Ilkin Serengil.Read 21 Oct 2026 · pypi.org

Licence

DeepFace is distributed under the MIT licence.Read 21 Oct 2026 · github.com

License and model caveat

DeepFace is MIT licensed, but the repository cautions that wrapped models can carry separate licenses that should be checked for production use.Read 4 Oct 2026 · github.com

Limit: backend migration friction

A 2025 issue records concerns that TensorFlow and Keras dependencies were heavy for PyTorch projects; the issue was closed as completed in September 2026 after backend work.Read 21 Oct 2026 · github.com

Limit: dependency packaging

Hysenlabs reports that the base requirements and optional backend extras have contradictory dependency declarations, creating packaging friction.Read 21 Oct 2026 · hysenlabs.com

Limit: installation failures

A project issue documents pip installation failures involving opencv-python on macOS with Python 3.12 and DeepFace 0.0.91.Read 21 Oct 2026 · github.com

Limit: Python compatibility

A Stack Overflow report says a user encountered TensorFlow import problems on Python 3.11 and resolved them by using Python 3.8.Read 21 Oct 2026 · stackoverflow.com

Popularity

Pepy reports 15,512,440 total PyPI downloads and 78,598 downloads in the preceding 30 days for version 0.0.102.Read 21 Oct 2026 · pepy.tech

Praise: unified interface

Hysenlabs describes DeepFace as useful for teams wanting verification, folder search and demographic analysis without implementing the underlying detection, alignment, normalization and embedding stages.Read 21 Oct 2026 · hysenlabs.com

Processing pipeline

The framework combines face detection, alignment, normalization, representation and verification or recognition in one workflow.Read 21 Oct 2026 · deepwiki.com

Real-time video

The stream function performs face recognition and attribute analysis on webcam or video streams.Read 21 Oct 2026 · github.com

Recent release change

The release history records version 0.0.100 disabling heavy unit tests and adding deepface.dev README updates.Read 21 Oct 2026 · github.com

Recognition models

The package wraps VGG-Face, FaceNet, OpenFace, DeepFace, DeepID, ArcFace, Dlib, SFace, GhostFaceNet and Buffalo_L models.Read 21 Oct 2026 · pypi.org

REST API

The self-hosted API exposes verification, representation, analysis and register/search operations through HTTP endpoints.Read 21 Oct 2026 · github.com

Runtime dependencies

Piwheels lists dependencies including retina-face, OpenCV contrib headless, ONNX Runtime, Flask, Gunicorn, Pillow, NumPy, pandas, gdown and requests.Read 21 Oct 2026 · piwheels.org

Self-hosting

The project can run locally from source or in Docker and uses Gunicorn for its service deployment scripts.Read 21 Oct 2026 · github.com

Similarity metrics

Verification and search can use cosine, Euclidean, normalized Euclidean or angular distance metrics.Read 21 Oct 2026 · github.com

System requirement

The current PyPI package requires Python 3.8 or newer and is classified as operating-system independent.Read 21 Oct 2026 · pypi.org

Third-party licence caveat

The README warns that wrapped recognition models and detector licences may impose additional obligations for production use.Read 21 Oct 2026 · github.com

Plans and prices

Every DeepFace plan and price →

Where Specifiction places it

• AI Face Swap Tools#1 of 579.0
• Image Recognition Software#3 of 288.9
• AI Image Recognition Software#4 of 378.8
• Facial Recognition Software#2 of 168.7