# williamyang1991/DualStyleGAN

[CVPR 2022] Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer

Repository: https://github.com/williamyang1991/DualStyleGAN
Canonical: https://ross.abutalabs.com/products/dualstylegan
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: style-transfer, face, stylegan2, stylegan-image-manipulation, toonify, caricatures, cvpr2022
Last push: 2023-03-06T09:30:54+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": 1634, "days_push": 1276, "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 1683, forks 254 (observed 2026-08-28T04:05:21.823760+00:00)

## What it is
Official PyTorch implementation of DualStyleGAN, a CVPR 2022 model for exemplar-based high-resolution (1024px) portrait style transfer. It extends StyleGAN2 with intrinsic and extrinsic style paths to control color and structure styles from a reference image.

## Use cases
- transfer artistic styles onto portrait photos using a style exemplar
- toonify or caricaturize a face image
- generate high-resolution stylized portraits with color and structure control
- run portrait style transfer with pretrained models in a notebook
- combine DualStyleGAN with Stable Diffusion for new styles

## When to choose
- you need exemplar-based portrait style transfer at 1024 resolution
- you want fine-grained control over color versus structural style
- you want a research-grade, paper-backed implementation with pretrained checkpoints

## When to avoid
- you need general image style transfer beyond portraits
- you lack a GPU or want a lightweight production service
- you need a permissively licensed model for commercial use (license is non-standard)

## Facets
- artifact type: library
- maturity: stable
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: stylegan2, style-transfer, portrait-style-transfer, toonify, caricature, cvpr2022, pytorch, generative-models, gpu

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:21.823760+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 2026-08-30T03:41:20.751720+00:00, confidence not recorded.
  - readme: https://github.com/williamyang1991/DualStyleGAN (fetched 2026-08-28T04:05:21.823760+00:00, sha 13f488018ebe)
- Data as of 2026-08-30T08:39:29.467469+00:00.