# datitran/face2face-demo

pix2pix demo that learns from facial landmarks and translates this into a face

Repository: https://github.com/datitran/face2face-demo
Canonical: https://ross.abutalabs.com/products/face2face-demo
Homepage: https://medium.com/@datitran/face2face-a-pix2pix-demo-that-mimics-the-facial-expression-of-the-german-chancellor-b6771d65bf66
Language: Python
License: MIT
License Family: permissive
Topics: tensorflow, pix2pix-tensorflow, python3
Last push: 2023-10-10T18:29:41+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3349, "days_push": 1058, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1461, forks 411 (observed 2026-08-28T04:04:47.422232+00:00)

## What it is
A pix2pix demo that learns from facial landmarks and translates them into a trained target face, with a real-time webcam application. It includes scripts for generating training data from video, training via the pix2pix-tensorflow implementation, and exporting a reduced model for inference.

## Use cases
- translate facial landmarks into a face with pix2pix
- real-time face-to-face webcam demo
- generate training data from a video of a face
- train a pix2pix model on facial landmark pairs
- swap my face with a trained face in real time
- learn how to run pix2pix with tensorflow

## When to choose
- you want a working end-to-end example of pix2pix for faces
- you need a real-time webcam face translation demo
- you want to learn the full pipeline from video to trained GAN model

## When to avoid
- you need production-grade face swapping or deepfake tooling
- you use PyTorch or recent TensorFlow versions without adaptation
- you need general image-to-image translation beyond faces

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: deep-learning, computer-vision, image-processing
- platform: python, cross-platform
- tags: pix2pix, face-swapping, facial-landmarks, webcam, tensorflow, gan, real-time-demo

## Member repositories
- datitran/face2face-demo (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:47.422232+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:35:19.867937+00:00, confidence not recorded.
  - readme: https://github.com/datitran/face2face-demo (fetched 2026-08-28T04:04:47.422232+00:00, sha 53ce614089cb)
- Data as of 2026-08-30T08:39:29.467469+00:00.