# warmshao/FasterLivePortrait

Bring portraits to life in Real Time！onnx/tensorrt support！实时肖像驱动！

Repository: https://github.com/warmshao/FasterLivePortrait
Canonical: https://ross.abutalabs.com/products/fasterliveportrait
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-06-29T07:36:41+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 29, release rhythm 40, longevity 55
- inputs: {"age_days": 780, "days_push": 430, "days_rel": 596, "gap_med": 5, "n_releases_24m": 6}
- 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 1174, forks 136 (observed 2026-08-28T04:03:52.276558+00:00)

## What it is
A real-time portrait animation application based on LivePortrait that animates still photos or videos using a driving video, image, audio, or text. It achieves 30+ FPS on an RTX 3090 via ONNX and TensorRT acceleration, with a Gradio web UI and camera mode.

## Use cases
- animate a portrait photo in real time from webcam
- make a talking head video driven by audio
- generate text-to-talking-video with kokoro tts
- drive multiple faces simultaneously in one video
- animate animal faces with the animal model
- run live portrait animation at 30+ fps with tensorrt

## When to choose
- you need real-time portrait animation on an NVIDIA GPU
- you want audio- or text-driven talking head generation
- you need multi-face or animal model support in a web UI

## When to avoid
- you have no NVIDIA GPU and need fast performance
- you need a permissively licensed library for commercial redistribution
- you want a simple offline batch tool without model setup

## Facets
- artifact type: application
- maturity: active
- function: image-processing, video-processing, machine-learning, llm-inference, speech-recognition
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: windows, python
- tags: face-animation, talking-head, liveportrait, tensorrt, onnx, real-time, audio-driven, gradio, video, linux, docker, gpu

## Member repositories
- warmshao/FasterLivePortrait (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:52.276558+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 2026-08-30T06:28:19.531613+00:00, confidence not recorded.
  - readme: https://github.com/warmshao/FasterLivePortrait (fetched 2026-08-28T04:03:52.276558+00:00, sha c2291ae8e82b)
- Data as of 2026-08-30T08:39:29.467469+00:00.