# rinongal/StyleGAN-nada

Repository: https://github.com/rinongal/StyleGAN-nada
Canonical: https://ross.abutalabs.com/products/stylegan-nada
Homepage: http://stylegan-nada.github.io/
Language: Python
License: MIT
License Family: permissive
Topics: domain-adaptation, stylegan, generative-adversarial-network
Last push: 2022-09-29T17:52:46+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": 1899, "days_push": 1434, "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 1195, forks 143 (observed 2026-08-28T04:03:56.862125+00:00)

## What it is
Official PyTorch implementation of StyleGAN-NADA, a CLIP-guided method for adapting pre-trained StyleGAN image generators to new domains using only a natural-language text prompt, with no target-domain training images. It trains a second generator so that the CLIP-space direction between paired outputs aligns with the textual direction.

## Use cases
- adapt a StyleGAN generator to a new art style from a text prompt
- convert faces to sketches or paintings without training data
- train an image generator blindly using only CLIP text guidance
- generate domain-shifted images like dogs to lions or churches to huts
- experiment with text-driven GAN domain adaptation in Colab
- invert real photos into an adapted generator's latent space

## When to choose
- you want to shift a pre-trained StyleGAN to a new domain described only in text
- you have no images from the target domain to train on
- you need a research-grade implementation of CLIP-guided domain adaptation
- you want to preserve latent-space properties of the original generator

## When to avoid
- you need a production image-generation service rather than research code
- you want to train a GAN from scratch on a large image dataset
- you lack a GPU or cannot run PyTorch training
- you need text-to-image generation without a pre-trained StyleGAN backbone

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, deep-learning
- domain: machine-learning, deep-learning, artificial-intelligence, image-processing
- platform: python, cross-platform
- tags: stylegan, clip, domain-adaptation, generative-models, text-guided, gan, research-code, siggraph-2022, gpu

## Member repositories
- rinongal/StyleGAN-nada (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.862125+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 2026-08-30T06:22:07.164516+00:00, confidence not recorded.
  - readme: https://github.com/rinongal/StyleGAN-nada (fetched 2026-08-28T04:03:56.862125+00:00, sha 8e334b2c76ea)
  - homepage: http://stylegan-nada.github.io/ (fetched 2026-08-29T12:29:24.491762+00:00, sha ac4da5026d6d)
- Data as of 2026-08-30T08:39:29.467469+00:00.