# iperov/DeepFaceLive

Real-time face swap for PC streaming or video calls

Repository: https://github.com/iperov/DeepFaceLive
Canonical: https://ross.abutalabs.com/products/deepfacelive
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: deepfake, real-time, faceswap, webcam, streaming, videocall, machine-learning
Archived: true
Last push: 2024-11-08T03:07:42+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2087, "days_push": 663, "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 31011, forks 1326 (observed 2026-08-28T04:11:56.546600+00:00)

## What it is
DeepFaceLive is a real-time face-swap application for PC streaming and video calls, using trained face models (DFM) applied to webcam or video input. It runs on consumer GPUs via ONNX/DirectX and ships with ready-to-use public face models.

## Use cases
- swap my face in real time on stream
- deepfake webcam for video calls
- real-time face swap with a trained face model
- use celebrity face model on my webcam
- face swap video files offline
- stream with a different face on twitch

## When to choose
- you need real-time face swapping on a Windows PC with a GPU
- you want ready-made face models without training your own
- you want to swap faces in video calls or live streams

## When to avoid
- you need to train custom face models from scratch (use DeepFaceLab instead)
- you need Linux or macOS support
- you lack a compatible GPU for real-time inference

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, image-processing, video-processing, computer-vision, gpu-computing
- domain: machine-learning, computer-vision, image-processing, media
- platform: windows, python
- tags: deepfake, face-swap, real-time, webcam, streaming, video-calls, onnx, deep-learning, video, desktop, gpu

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:56.546600+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 2026-08-29T16:52:20.296458+00:00, confidence not recorded.
  - readme: https://github.com/iperov/DeepFaceLive (fetched 2026-08-28T04:11:56.546600+00:00, sha 2b1d7a8f35bc)
- Data as of 2026-08-30T08:39:29.467469+00:00.