# Avatarify

Avatars for Zoom, Skype and other video-conferencing apps.

Repository: https://github.com/alievk/avatarify-python
Canonical: https://ross.abutalabs.com/products/avatarify
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-08-30T23:48:03+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2340, "days_push": 733, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16515, forks 4304 (observed 2026-08-28T04:11:16.637813+00:00)

## What it is
Avatarify is an open-source application that drives photorealistic avatars in real time for video-conferencing apps like Zoom and Skype, based on the First Order Motion Model. It comes in a Python CLI version for experienced users and an easier-to-install Desktop version, with a virtual camera feeding animated avatars into calls.

## Use cases
- replace my face with an avatar in zoom calls
- animate a photo to drive a video call
- use a stylegan-generated face on video conferences
- run a virtual camera with a deep learning avatar
- appear as someone else on skype or teams
- real-time face animation from a webcam

## When to choose
- you want photorealistic, real-time face-driven avatars in any video-conferencing app
- you have a GPU or can use Google Colab / remote GPU
- you want an open-source alternative to commercial avatar apps

## When to avoid
- you need a polished one-click installer without command-line setup (try Avatarify Desktop instead)
- you need mobile support - the iOS/Android apps are proprietary and separate
- your machine has no GPU and you cannot use remote inference
- you need an actively developed project with a clear license

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, video-processing, computer-vision, deep-learning
- domain: computer-vision, deep-learning, media
- platform: windows, python
- tags: avatars, video-conferencing, face-animation, first-order-motion-model, virtual-camera, zoom, skype, deepfakes, video, macos, linux, docker

## Member repositories
- alievk/avatarify-python (main) score 23
- alievk/avatarify-desktop (frontend) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:16.637813+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 2026-08-29T17:04:53.318936+00:00, confidence not recorded.
  - readme: https://github.com/alievk/avatarify-python (fetched 2026-08-28T04:11:16.637813+00:00, sha 9070517abaae)
- Data as of 2026-08-30T08:39:29.467469+00:00.