# yuval-alaluf/hyperstyle

Official Implementation for "HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing" (CVPR 2022) https://arxiv.org/abs/2111.15666

Repository: https://github.com/yuval-alaluf/hyperstyle
Canonical: https://ross.abutalabs.com/products/hyperstyle
Homepage: https://yuval-alaluf.github.io/hyperstyle/
Language: Python
License: MIT
License Family: permissive
Topics: generative-adversarial-network, stylegan, stylegan-encoder, hypernetworks, cvpr2022
Last push: 2022-09-17T16:06:21+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": 1737, "days_push": 1446, "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 1027, forks 119 (observed 2026-08-28T04:03:17.213476+00:00)

## What it is
Official PyTorch implementation of HyperStyle (CVPR 2022), a hypernetwork that inverts real images into editable regions of StyleGAN's latent space by modulating the generator's weights. It achieves optimization-quality reconstructions with near real-time encoder inference and supports downstream image editing applications.

## Use cases
- invert real face photos into StyleGAN latent space
- edit real images with GAN latent directions
- reconstruct images with high fidelity and editability
- edit out-of-domain images via domain adaptation
- generate face animations from a single image
- run StyleGAN inversion experiments for research

## When to choose
- you need fast, editable StyleGAN inversions of real images
- you want a research-grade reference implementation of a CVPR 2022 inversion method
- you need to edit faces or adapt the model to new domains

## When to avoid
- you need a production-ready, maintained product with support
- you work with non-face imagery without retraining
- you lack a GPU or PyTorch environment
- you need text-to-image generation rather than inversion of existing images

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, deep-learning
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python
- tags: stylegan, gan-inversion, hypernetworks, image-editing, cvpr2022, research-code, gpu

## Member repositories
- yuval-alaluf/hyperstyle (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:17.213476+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 2026-08-30T07:07:55.755602+00:00, confidence not recorded.
  - readme: https://github.com/yuval-alaluf/hyperstyle (fetched 2026-08-28T04:03:17.213476+00:00, sha 905a36cb7a7b)
  - homepage: https://yuval-alaluf.github.io/hyperstyle/ (fetched 2026-08-29T13:08:21.870359+00:00, sha 5247397ac1d4)
- Data as of 2026-08-30T08:39:29.467469+00:00.