# autonomousvision/stylegan-t

[ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

Repository: https://github.com/autonomousvision/stylegan-t
Canonical: https://ross.abutalabs.com/products/stylegan-t
Language: Python
License: NOASSERTION
License Family: other
Last push: 2023-04-07T08:58:50+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 94
- inputs: {"age_days": 1321, "days_push": 1244, "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 1197, forks 61 (observed 2026-08-28T04:03:57.556966+00:00)

## What it is
Official training code for StyleGAN-T, an ICML 2023 paper on fast large-scale text-to-image synthesis using GANs. It provides dataset preparation and training tooling in Python/PyTorch but does not include pretrained checkpoints.

## Use cases
- train a text-to-image GAN from scratch
- reproduce StyleGAN-T paper experiments
- generate images from text prompts with a GAN instead of diffusion models
- train conditional GANs on custom image datasets
- benchmark fast text-to-image synthesis against diffusion baselines

## When to choose
- you want to train or extend a fast text-to-image GAN
- you need the exact training code from the StyleGAN-T paper
- you have GPU resources and your own image-caption datasets

## When to avoid
- you just want to generate images with pretrained weights (none are provided)
- you need a production text-to-image service
- you prefer diffusion-based models like Stable Diffusion

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-training
- domain: machine-learning, deep-learning, artificial-intelligence, image-processing
- platform: python
- tags: text-to-image, gan, stylegan, research-code, icml-2023, pytorch, no-pretrained-checkpoints, gpu, linux

## Member repositories
- autonomousvision/stylegan-t (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:57.556966+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 2026-08-30T06:21:25.871602+00:00, confidence not recorded.
  - readme: https://github.com/autonomousvision/stylegan-t (fetched 2026-08-28T04:03:57.556966+00:00, sha 7099631b61b8)
- Data as of 2026-08-30T08:39:29.467469+00:00.