# williamyang1991/VToonify

[SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer

Repository: https://github.com/williamyang1991/VToonify
Canonical: https://ross.abutalabs.com/products/vtoonify
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: face, siggraph-asia, style-transfer, stylegan2, toonify, video-style-transfer
Last push: 2023-10-25T00:46:55+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1454, "days_push": 1044, "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 3584, forks 446 (observed 2026-08-28T04:08:11.058913+00:00)

## What it is
Official PyTorch implementation of VToonify, a SIGGRAPH Asia 2022 framework for controllable high-resolution portrait video style transfer built on StyleGAN. It extends StyleGAN-based image toonification models (Toonify, DualStyleGAN) to temporally consistent video toonification with flexible style control.

## Use cases
- toonify portrait videos with cartoon styles
- transfer artistic styles to face videos at high resolution
- apply exemplar-based style transfer to portrait images and videos
- control color and intensity of toonified output
- run toonification inference in Colab or Hugging Face demo

## When to choose
- you need research-grade portrait video toonification with temporal consistency
- you want StyleGAN-based controllable artistic face stylization
- you need to process non-aligned faces in variable-size video frames

## When to avoid
- you need a production-ready end-user application with a polished UI
- you need general-purpose video style transfer beyond portrait faces
- you require a permissive license for commercial use

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, video-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python, cross-platform
- tags: stylegan, style-transfer, toonification, portrait-video, pytorch, research-code, siggraph-asia, video, gpu

## Member repositories
- williamyang1991/VToonify (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:11.058913+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 2026-08-29T18:33:56.269543+00:00, confidence not recorded.
  - readme: https://github.com/williamyang1991/VToonify (fetched 2026-08-28T04:08:11.058913+00:00, sha 7ad657c43025)
- Data as of 2026-08-30T08:39:29.467469+00:00.