# Zejun-Yang/AniPortrait

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Repository: https://github.com/Zejun-Yang/AniPortrait
Canonical: https://ross.abutalabs.com/products/aniportrait
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-07-02T02:22:52+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 63
- inputs: {"age_days": 894, "days_push": 793, "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 5021, forks 612 (observed 2026-08-28T04:09:04.839555+00:00)

## What it is
AniPortrait is a Python framework from Tencent that generates photorealistic portrait animations from an audio clip and a reference image, and also supports face reenactment from a driving video. It ships with pretrained weights, a Gradio demo, and inference scripts for audio-to-video and video-to-video generation.

## Use cases
- animate a portrait photo to speak with a given audio track
- create talking head videos from audio
- reenact a face using a source driving video
- generate lip-synced avatar videos for content creation
- control head pose in generated portrait animations

## When to choose
- you need audio-driven talking portrait generation with pretrained models
- you want face reenactment driven by a reference video
- you want a research-grade photorealistic animation pipeline you can self-host

## When to avoid
- you need real-time animation on consumer hardware without a GPU
- you want a production-ready commercial avatar service with support
- you need lightweight lip-sync only without diffusion-based generation

## Facets
- artifact type: application
- maturity: maintenance
- function: video-processing, machine-learning, deep-learning, image-processing, speech-recognition
- domain: artificial-intelligence, computer-vision, deep-learning, image-processing
- platform: python, self-hosted
- tags: talking-head, face-reenactment, audio-driven-animation, diffusion, gradio, photorealistic-portrait, video, linux, gpu

## Member repositories
- Zejun-Yang/AniPortrait (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:04.839555+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 2026-08-29T18:17:29.839576+00:00, confidence not recorded.
  - readme: https://github.com/Zejun-Yang/AniPortrait (fetched 2026-08-28T04:09:04.839555+00:00, sha 5fae2e21d9a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.