OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Faced

Faced is an MIT-licensed Python face-detection library and command-line tool built around an ensemble of two TensorFlow neural networks. It processes image, webcam and video input, producing face bounding boxes and confidence probabilities.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Faced — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Faced for development or experimentation when a CPU-focused Python detector or CLI workflow fits the task. The README also documents GPU installation, but describes the project as work in progress and not production-ready.

Who it is for

  • Python developers adding face bounding boxes to image-processing workflows.
  • Users who want command-line face detection for images, webcam streams or video.

Documented uses

  • Find faces and obtain bounding-box coordinates and confidence values from an RGB image.
  • Save annotated face detections from an image through the CLI.
  • Preview face detection on a webcam stream.
  • Process video with a configurable confidence threshold.
Before you choose

Requirements & limits

The repository is public and declares an MIT license. Installation is documented through pip from the Git repository.

  • The library prediction example accepts an RGB NumPy image and returns tuples containing center coordinates, width, height and probability.
  • The CLI examples include image saving, webcam input and video threshold selection.
  • The README reports about 5 FPS on a 2015 MacBook Pro with an i5 and more than 70 FPS on an Nvidia Titan XP; results are hardware-specific.
  • The repository describes the project as work in progress and explicitly says it is not production-ready.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Faced from its Git repository

Prepare the documented Python library and CLI for use.

Before you start

  • Python environment capable of installing packages with pip.

Steps

  1. Install Faced with the command below.

    Documented command
    pip install git+https://github.com/iitzco/faced.git

  2. For GPU use, install tensorflow-gpu instead of tensorflow, as the README directs.

Expected outcome

The repository documents the package installation command and the TensorFlow option for GPU use.

Guide limitations

  • The README labels the project work in progress and not production-ready.
  • No detailed environment or dependency compatibility matrix is provided.
Documentation 1 ↗
Source-based practical guide

Run face detection on an image, webcam or video

Use the documented CLI examples to process one of the supported input types.

Before you start

  • Faced installed from its Git repository.
  • An image or video file for file-based examples, or a webcam for the live-input example.

Steps

  1. For an image, run faced --input imgs/demo.png --save to save the detection output.

  2. For a webcam preview, run faced --input webcam.

  3. For a video, run faced --input imgs/demo.mp4 --threshold 0.5.

Expected outcome

The examples invoke detection for a saved image, live webcam input or video with a selected threshold.

Guide limitations

  • The README directs users to faced --help for additional CLI options.
  • The project warns that it is not production-ready.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
iitzco/faced · Official homepage title · retained in its source language
How we review sourcesSuggest a correction