# deepfakes/faceswap

Deepfakes Software For All

Repository: https://github.com/deepfakes/faceswap
Canonical: https://ross.abutalabs.com/products/faceswap
Homepage: https://www.faceswap.dev
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: faceswap, face-swap, deep-learning, deeplearning, deep-neural-networks, deepfakes, deepface, deep-face-swap, fakeapp, neural-networks, neural-nets, openfaceswap, myfakeapp, machine-learning
Last push: 2026-08-05T11:39:37+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 62, longevity 100
- inputs: {"age_days": 3179, "days_push": 28, "days_rel": 255, "gap_med": 1, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 57500, forks 13490 (observed 2026-08-28T04:12:18.543885+00:00)

## What it is
Faceswap is a free, open-source, multi-platform deepfakes tool that uses deep learning to recognize and swap faces in pictures and videos. It provides an extract-train-convert workflow with both a GUI and command-line interface, powered by TensorFlow and Keras.

## Use cases
- swap faces in videos with deep learning
- create deepfake videos from photos and footage
- train a face swap model on my own dataset
- extract and align faces from images and video frames
- replace a face in a movie clip with another person's face
- run deepfakes software on Windows, Linux or macOS

## When to choose
- you want a mature, actively maintained open-source deepfakes tool with a GUI and large community
- you need a full extract-train-convert pipeline for face swapping in images and videos
- you want cross-platform support (Windows, macOS, Linux) with GPU acceleration
- you want extensive guides, forums, and community support for learning deepfakes

## When to avoid
- you need a lightweight library to embed face swapping into your own application rather than a standalone tool
- you require real-time face swapping or live streaming effects
- you cannot meet the GPU/training hardware requirements
- your use case involves non-consensual imagery, which is ethically and often legally problematic

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, deep-learning, image-processing, video-processing, computer-vision
- domain: deep-learning, machine-learning, image-processing, artificial-intelligence
- platform: windows, python, cross-platform
- tags: deepfakes, face-swap, face-recognition, tensorflow, keras, gui, neural-networks, video, macos, linux, gpu

## Member repositories
- deepfakes/faceswap (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:18.543885+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 2026-08-29T16:18:30.326159+00:00, confidence not recorded.
  - readme: https://github.com/deepfakes/faceswap (fetched 2026-08-28T04:12:18.543885+00:00, sha 26db23921c4e)
  - homepage: https://www.faceswap.dev (fetched 2026-08-28T18:02:48.061074+00:00, sha f1457e9d1290)
- Data as of 2026-08-30T08:39:29.467469+00:00.