face_recognition_models
Models used by the face_recognition package.
What it is and what it does
This package is a model repository—it bundles pre-trained neural network weights for face detection, recognition, and encoding tasks. It exists as a dependency for the face_recognition library and is not meant to be used standalone; you install it to get the trained models that face_recognition needs to operate. The models were created by Davis King and are distributed in the public domain or under CC0 1.0 Universal.
The package itself contains no code logic, only data files. Installation requires downloading large model artifacts, which creates significant friction. The project is abandoned and has not been updated since 2017, with the last commit in late 2022 likely being a minor maintenance action. The declared Python support (2.6 through 3.6) is obsolete, and whether it works with modern Python versions is unclear.
Use it for:
- Satisfy the model dependency when installing face_recognition for facial detection and recognition tasks
- Provide pre-trained weights for face encoding in computer vision pipelines
- Bundle models for deployment of face recognition applications without requiring separate model downloads
Worth the install?
AI-flagged interpretation of the facts on this page — verify before relying
Provides pre-trained deep learning models for face detection, recognition, and encoding used by the face_recognition package.
No, unless you are explicitly required by face_recognition as a dependency. The package is abandoned, its Python version claims are obsolete, and installation is friction-heavy due to large model files. If you need facial recognition, evaluate whether face_recognition itself is still maintained and whether its current dependencies have been updated; this package will likely be pulled in automatically if needed, but do not install it directly.
Install
face-recognition-models on PyPI
pip
pip install face-recognition-modelsuv
uv add face-recognition-modelspoetry
poetry add face-recognition-modelsInstalling face_recognition_models
Before you install
High install friction due to large model files. Package is abandoned—last release was 2017-09-28 and last commit 2022-12-26. Classifiers declare support for Python 2.6 through 3.6, which are all end-of-life; actual compatibility with modern Python versions is unverified.
License in practice
Licensed under MIT (permissive), allowing commercial and private use with attribution. Models themselves are in the public domain or CC0 1.0 Universal per the description, so licensing constraints are minimal.
Quickstart
pip install face-recognition-models==0.3.0
# Models are data files only; typically imported indirectly via face_recognition
Large model file downloads create significant installation time and disk space requirements.
Verify before relying
- Whether the package actually works with Python versions beyond 3.6 despite classifier claims
- Current size and download time for the bundled model files
- Whether models are compatible with current versions of dependencies
Package facts
| License | MIT license (permissive) |
| Python support | not specified |
| Install friction | high — source build required |
| Runtime dependencies | none |
| Maintenance | abandoned — 3,242 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 132,298/month — #11,557 on PyPI (30-day window, as of 2026-08-14) |
| Known vulnerabilities | none known (OSV.dev, checked 2026-08-14) |
Evidence: face_recognition_models-0.3.0.tar.gz
Keywords: face_recognition
Tags
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to…
permissive · top 100 on PyPI
huggingface-hubClient library and CLI tool for downloading,…
permissive · top 100 on PyPI
langchainLangChain provides a framework for building…
permissive · top 1,000 on PyPI
hf-xethf-xet provides chunk-based deduplication and…
permissive · top 1,000 on PyPI
tokenizersTokenizers converts raw text into token…
permissive · top 1,000 on PyPI
transformersTransformers provides a unified framework for…
permissive · top 1,000 on PyPI
face-recognitionDetects, locates, and identifies faces in…
permissive · top 15,000 on PyPI
deepfaceDeepFace performs face recognition,…
permissive · top 15,000 on PyPI
retina-faceDetects faces in images and extracts facial…
permissive · top 15,000 on PyPI
mtcnnDetects faces and facial landmarks (eyes, nose,…
permissive · top 5,000 on PyPI
facenet-pytorchProvides pretrained PyTorch models for face…
permissive · top 15,000 on PyPI
facexlibFacexlib provides a collection of PyTorch-based…
permissive · top 5,000 on PyPI
face-alignmentDetects 2D and 3D facial landmarks from images…
permissive · top 15,000 on PyPI
pytorchcvProvides a collection of pretrained computer…
unclear · top 15,000 on PyPI
dlibdlib is a C++ machine learning and computer…
unclear · top 15,000 on PyPI
smplxLoads and manipulates SMPL-X, a unified 3D body…
unclear · top 15,000 on PyPI