# iperov/DeepFaceLab

DeepFaceLab is the leading software for creating deepfakes.

Repository: https://github.com/iperov/DeepFaceLab
Canonical: https://ross.abutalabs.com/products/deepfacelab
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, deepfacelab, creating-deepfakes, arxiv, machine-learning
Archived: true
Last push: 2024-11-13T19:29:05+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3012, "days_push": 658, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 19292, forks 933 (observed 2026-08-28T04:11:27.573030+00:00)

## What it is
DeepFaceLab is the leading open-source Windows application for creating deepfakes, allowing users to swap, de-age, or replace faces and heads in videos using deep neural networks. It provides a full pipeline from data extraction to model training and final video merging, built on TensorFlow with CUDA GPU acceleration.

## Use cases
- swap a face in a video
- create deepfake videos
- de-age a person's face in footage
- replace a head in a video
- train a face-swap model on GPU
- make face-swap videos for VFX work

## When to choose
- you want the most widely used and proven deepfake tooling
- you need a complete end-to-end face-swap pipeline on Windows with NVIDIA GPUs
- you want fine-grained control over training and merging stages

## When to avoid
- you need a simple one-click face swap without training
- you work on Linux or macOS without Windows support
- you lack a powerful CUDA-capable GPU
- you need real-time face swapping

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, video-processing, gpu-computing
- domain: deep-learning, machine-learning, image-processing, media
- platform: windows, python
- tags: deepfake, face-swap, face-reenactment, generative-models, tensorflow, video, gpu, desktop

## Member repositories
- iperov/DeepFaceLab (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:27.573030+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 2026-08-29T17:00:23.274397+00:00, confidence not recorded.
  - readme: https://github.com/iperov/DeepFaceLab (fetched 2026-08-28T04:11:27.573030+00:00, sha 6324130f2613)
- Data as of 2026-08-30T08:39:29.467469+00:00.