DeepFace
github.com
- Free plan
- Open source
- Windows
- macOS
- Linux
- Web
- API
- Self-hosted
What DeepFace is
DeepFace is a free, MIT-licensed Python framework for face recognition and facial attribute analysis. It can verify faces, find identities in folders, analyze images, and produce face embeddings, including attributes such as age, gender, emotion, and race. The library wraps recognition models including VGG-Face, FaceNet, OpenFace, DeepFace, DeepID, ArcFace, Dlib, SFace, GhostFaceNet, and Buffalo_L. Detection backends include OpenCV, SSD, Dlib, MTCNN, RetinaFace, MediaPipe, YOLO, YuNet, and CenterFace, with configurable alignment. An optional anti-spoofing module assesses whether an image is real or fake. Database operations support PostgreSQL, MongoDB, Neo4j, pgvector, Pinecone, Milvus, Qdrant, and Weaviate. DeepFace can expose REST or gRPC APIs for verification, attributes, vectors, registration, and search. Installations can use PyPI or source with TensorFlow, PyTorch, or ONNX Runtime. A managed deepface.dev API is also available.
Who it suits
DeepFace suits developers building self-hosted or API-based face recognition and attribute analysis. It fits projects that need multiple model, detector, database, or serving options.
Good to know, and what to watch
- Free MIT-licensed Python library
- Many recognition models and detector backends
- Optional anti-spoofing module
- REST and gRPC serving options
- Broad database integration support
- Wrapped models may have separate licenses
- Production users must check each model’s licensing
- Hosted service excludes VGG-Face
Plans
Every plan and pricedeepface.dev Enterprise
Anonymous trial
deepface.dev free access
deepface.dev free allowance
Free plan
The verdict
DeepFace offers a wide set of recognition, detection, analysis, database, and serving choices in a free Python framework. Teams should review the separate licenses of wrapped models before production use, especially when considering hosted options.
What the maker publishes
- Accepted image inputs
- The API accepts uploaded files, local paths, URLs and base64-encoded image data. source
- Anti-spoofing
- DeepFace includes an optional anti-spoofing module to assess whether a face image is real or fake. source
- Anti-spoofing
- Face extraction and streaming can optionally enable anti-spoofing checks to distinguish real faces from spoof inputs. source
- API options
- DeepFace can be served through REST or gRPC, and its API covers verification, facial attribute analysis, vector representation, registration, and search. source
- Attribute analysis
- The analyze function predicts age, gender, emotion and race attributes. source
- Database integrations
- Database-backed operations support PostgreSQL, MongoDB, Neo4j, pgvector, Pinecone, Milvus, Qdrant, and Weaviate. source
- Database integrations
- Database-backed registration and search support PostgreSQL, MongoDB, Weaviate, Neo4j, PGVector and Pinecone, with additional backends listed in the project README. source
- Detection and alignment
- Available detector backends include OpenCV, SSD, Dlib, MTCNN, RetinaFace, MediaPipe, YOLO, YuNet, and CenterFace, and alignment can be configured. source
- Detector choices
- Documented detector backends include OpenCV, SSD, MTCNN, RetinaFace, MediaPipe, YOLO variants, Dlib, YuNet, CenterFace and FastMTCNN. source
- Documentation depth
- Independent documentation indexes installation, quick start, core APIs, database integrations, models, REST deployment, Docker, benchmarking and testing. source
- Embeddings
- The represent function converts faces into multidimensional embedding vectors. source
- Face search
- The find function searches for an input face inside a file-based image database and returns matched identities. source
- Face tasks
- Its functions support face verification, finding identities in a folder, image analysis, and producing face embeddings. source
- Face verification
- The verify function determines whether two supplied face images belong to the same person and returns a verification result with distance information. source
- gRPC API
- A gRPC service is available with a protobuf contract covering the same core operations as the REST service. source
- Hosted API
- deepface.dev provides a managed API for verification, embedding generation, and vector comparison without requiring users to manage GPU infrastructure. source
- Hosted API
- deepface.dev provides a managed API for verification, embedding generation and vector comparison while handling hosting, scaling and model updates. source
- Hosted API authentication
- The managed service uses account-created REST or MCP keys and exposes its REST gateway at api.deepface.dev. source
- Hosted API endpoints
- The managed public API documents POST /verify, POST /represent, POST /compare and GET /capabilities. source
- Hosted API request controls
- The hosted quickstart documents API keys, model allowlists, optional remote URL fetching checks and an x-request-id for troubleshooting. source
- 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. source
- 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. source
- 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. source
- Install options
- The library can be installed from PyPI or source code with TensorFlow, PyTorch, or ONNX Runtime backends. source
Checked against the maker's pages on 21 Oct 2026.