Steve-Mr/EmojiFace

Identify faces in an image and replace them with emojis.

What FaceMoji does

FaceMoji (also called EmojiFace) is a small Android/web app that detects human faces in a picture and covers each face with an emoji (or applies a blur). All the image processing happens locally – nothing is uploaded to a server.

How it works

  • The app uses a pre‑trained YOLOv8‑face model (from the derronqi/yolov8-face project) to locate faces in an image.
  • Once a face rectangle is found, the app either:
    • draws a chosen emoji over the region, or
    • applies one of several blur styles (Gaussian, pixelation, halftone‑like).
  • Users can manually add, move, or delete emojis and blur areas, and they can import their own emoji‑style font files.

Where you can run it

Platform How to get it Notes
Web (PWA) Click the Deploy with Vercel button in the README or follow the instructions in web/README.md. The site runs entirely in the browser and stores no data remotely. Works on desktop and mobile browsers; can be installed as a Progressive Web App.
Android Download the latest release from the GitHub Releases page (two APK flavors):
• default – normal app icon (can be hidden in settings).
• icon‑disabled – app icon hidden by default, intended for “share‑to‑app” use.		 Both APKs are signed and can be installed manually. The hidden‑icon version is useful when you want to launch the app only via the Android share menu.

Main features

  1. Automatic face detection → emoji overlay (default) or blur.
  2. Manual editing – add, move, or delete emojis / blur patches.
  3. Multiple blur styles – Gaussian, pixelation, custom halftone‑like effect.
  4. Icon‑hiding mode – run the app solely through image‑share intents.
  5. Custom emoji fonts – import your own emoji‑style font to change the overlay appearance.

Limitations & caveats

  • The face‑detection model is offline and runs on‑device, but it is not as robust as cloud‑based services – it may miss faces or mis‑detect them in some images.
  • The web version was quickly assembled by a contributor (Jules / Vibe Coding); its code quality and stability are not guaranteed.
  • The app is provided “as‑is” with no warranty.

How to contribute / build yourself

  • The repository contains a web folder with its own README for deployment instructions.
  • Android source code can be compiled with Android Studio; the two APK flavors are defined in the Gradle configuration.
  • The face‑detection model is pulled from the external derronqi/yolov8-face project, so updating the model simply means replacing the .pt file used by the app.

Acknowledgements

  • Emoji icons are adapted from the Carnival Masks Pack on Freepik.
  • Face detection relies on the YOLOv8‑face model from derronqi/yolov8-face.

TL;DR – FaceMoji is a privacy‑first Android/web tool that uses an on‑device YOLOv8 face detector to replace faces with emojis or blur them, with optional manual editing and a hidden‑icon mode for share‑only usage.

Related

  • Project
    facefusion/facefusion-pinokio

    FaceFusion Pinokio is a face manipulation platform that allows users to swap and modify faces in images and videos with a simplified installation process via Pinokio.

  • Dispatch
    Decoy Font: Obscuring Text from AI using Spatial Frequencies

    Decoy Font is a TTF font that uses hybrid image techniques to display different messages based on viewing distance, aiming to trick AI OCR and LLMs.

  • Project
    Faceplugin-ltd/Open-Source-Face-Recognition-SDK

    An open-source face recognition SDK for Windows and Linux that provides on-premise face detection, landmark detection, and similarity comparison using deep learning.

  • Project
    yakhyo/uniface

    UniFace is a Python library that unifies 15 face‑analysis tasks—detection, landmarks, 3‑D mesh, parsing, matting, gaze, head pose, demographics, emotion, quality, anti‑spoofing, recognition, anonymisation, and FAISS‑based similarity—into a single, easy‑to‑install package (CPU, Apple Silicon, or CUDA). It provides a consistent API, auto‑downloads verified model weights, and includes extensive docs, notebooks, and a community Discord.

  • Project
    dataiku/kiji-proxy

    Kiji Privacy Proxy is an open‑source local proxy (macOS desktop app or Linux server) that automatically detects and masks 26 types of personally‑identifiable information in requests to AI services (OpenAI, Anthropic, Gemini, etc.) using an ONNX‑optimized DistilBERT model. It replaces sensitive data with realistic dummy values before forwarding the request, then restores the original data in the response. The tool works transparently via HTTP proxy settings (PAC on macOS, env vars on Linux), includes a Chrome extension for web‑based chat, offers a UI for reviewing masked mappings, and is configurable via custom regexes. All PII processing happens locally, keeping data private and helping meet GDPR/CCPA/HIPAA requirements. Installation is via Homebrew cask on macOS or Debian/Ubuntu packages, Docker, or tarballs. The project is Apache‑2.0 licensed and maintained by Dataiku’s 575 Lab, with full documentation, contribution guides, and security contact information.