# KlingAIResearch/LivePortrait

Bring portraits to life!

Repository: https://github.com/KlingAIResearch/LivePortrait
Canonical: https://ross.abutalabs.com/products/liveportrait
Homepage: https://liveportrait.github.io
Language: Python
License: NOASSERTION
License Family: other
Topics: image-animation, video-editing, video-generation, face-animation
Last push: 2026-06-01T17:25:09+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 85, release rhythm 35, longevity 56
- inputs: {"age_days": 791, "days_push": 93, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18969, forks 1973 (observed 2026-08-28T04:11:27.286560+00:00)

## What it is
LivePortrait is a Python-based portrait animation tool from Kuaishou Technology that synthesizes lifelike videos from a single source image, driven by a video, audio, text, or generated motion. It uses an efficient implicit-keypoint framework with stitching and eye/lip retargeting control, and works across realistic, painted, sculpted, and 3D-rendered portrait styles as well as fine-tuned animal faces.

## Use cases
- animate a still portrait photo using a driving video
- make a talking head video from one image
- transfer facial expressions and head pose between people
- control eye and lip opening extent in an animated portrait
- animate paintings, sculptures, and 3D renders
- make animal photos sing or dance driven by human motion
- edit facial motion in an existing portrait video

## When to choose
- you need fast, controllable face animation rather than slow diffusion-based generation
- you want to animate non-photorealistic portraits or animal images
- you need fine-grained control over eye and lip retargeting
- you want a one-click Windows installer or online demo to try quickly

## When to avoid
- you need audio-driven lip sync as the primary workflow with production support
- you require a permissively licensed library for commercial redistribution (license is non-standard)
- you need full-body or multi-person animation
- you lack a GPU and need real-time performance

## Facets
- artifact type: application
- maturity: active
- function: video-processing, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, artificial-intelligence, deep-learning
- platform: python, windows, cross-platform
- tags: portrait-animation, face-reenactment, talking-head, implicit-keypoints, video-generation, face-stitching, retargeting, deepfake, video, linux, macos, gpu

## Member repositories
- KlingAIResearch/LivePortrait (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:27.286560+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 2026-08-29T17:00:43.394591+00:00, confidence not recorded.
  - readme: https://github.com/KlingAIResearch/LivePortrait (fetched 2026-08-28T04:11:27.286560+00:00, sha 11690fc78cd1)
  - homepage: https://liveportrait.github.io (fetched 2026-08-29T07:59:02.210035+00:00, sha ea09e19f1cc2)
- Data as of 2026-08-30T08:39:29.467469+00:00.