# tencent-ailab/V-Express

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.

Repository: https://github.com/tencent-ailab/V-Express
Canonical: https://ross.abutalabs.com/products/v-express
Language: Python
License Family: other
Last push: 2025-01-24T14:40:41+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 3, release rhythm 35, longevity 59
- inputs: {"age_days": 834, "days_push": 586, "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 2360, forks 298 (observed 2026-08-28T04:06:40.848268+00:00)

## What it is
V-Express is a Python research project from Tencent AI Lab that generates talking head portrait videos from a reference image, audio, and V-Kps pose images using progressive conditional dropout to balance weak and strong control signals. It includes inference and training code with pretrained models hosted on Hugging Face.

## Use cases
- generate a talking head video from a photo and audio
- make a portrait lip-sync to an audio clip
- animate a single face image with speech
- create avatar videos driven by voice
- research on audio-conditioned portrait video generation

## When to choose
- you need audio-driven talking head video generation from a single reference image
- you want to reproduce or extend research on balancing weak/strong control signals in diffusion-based video generation
- you need pose, image, and audio jointly controlled portrait animation

## When to avoid
- you need a production-ready product with a license guarantee (no license is provided)
- you need real-time or low-latency generation on modest hardware
- you want a polished GUI application rather than Python scripts and model checkpoints

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, image-processing
- domain: deep-learning, computer-vision, artificial-intelligence
- platform: python
- tags: talking-head-generation, portrait-video, audio-driven-animation, diffusion-models, face-animation, research-code, video, linux, gpu

## Member repositories
- tencent-ailab/V-Express (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:40.848268+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 2026-08-30T02:36:12.941021+00:00, confidence not recorded.
  - readme: https://github.com/tencent-ailab/V-Express (fetched 2026-08-28T04:06:40.848268+00:00, sha 2d70b8769c82)
- Data as of 2026-08-30T08:39:29.467469+00:00.