# albertpumarola/GANimation

GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]

Repository: https://github.com/albertpumarola/GANimation
Canonical: https://ross.abutalabs.com/products/ganimation
Homepage: http://www.albertpumarola.com/research/GANimation/index.html
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: face-manipulation, facial-expressions, deep-learning, generative-adversarial-network, pytorch, ganimation, eccv-2018, gan
Last push: 2019-12-23T06:27:57+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2963, "days_push": 2445, "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 1985, forks 401 (observed 2026-08-28T04:06:02.616367+00:00)

## What it is
Official PyTorch implementation of GANimation, an ECCV'18 research paper that animates facial expressions in a single image using a GAN conditioned on Action Unit (AU) annotations. It allows continuous control over the magnitude of each facial muscle movement while preserving unrelated image regions.

## Use cases
- animate facial expressions in a single photo
- change a face's expression with controllable intensity
- generate smiling versions of portrait images
- research GAN conditioning on facial action units
- reproduce ECCV 2018 GANimation paper results
- train a facial expression editing model on annotated datasets

## When to choose
- you need anatomically-aware facial expression editing from one image
- you want continuous control over action unit activation magnitudes
- you are reproducing or extending the GANimation research
- you have OpenFace AU annotations for your training data

## When to avoid
- you need a production-ready or actively maintained face editing tool
- you require support for recent PyTorch versions (code targets PyTorch 0.3.1)
- you want a simple pretrained model with no training setup
- your use case involves real-time video animation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python
- tags: gan, facial-animation, face-manipulation, action-units, pytorch, research-code, eccv-2018, generative-adversarial-network, linux, macos

## Member repositories
- albertpumarola/GANimation (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:02.616367+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 2026-08-30T03:03:15.952576+00:00, confidence not recorded.
  - readme: https://github.com/albertpumarola/GANimation (fetched 2026-08-28T04:06:02.616367+00:00, sha 3fe62f8ced06)
  - homepage: http://www.albertpumarola.com/research/GANimation/index.html (fetched 2026-08-29T10:42:59.159468+00:00, sha 8b681fe61127)
- Data as of 2026-08-30T08:39:29.467469+00:00.