# phillipi/pix2pix

Image-to-image translation with conditional adversarial nets

Repository: https://github.com/phillipi/pix2pix
Canonical: https://ross.abutalabs.com/products/pix2pix
Homepage: https://phillipi.github.io/pix2pix/
Language: Lua
License: NOASSERTION
License Family: other
Topics: computer-vision, computer-graphics, gan, pix2pix, dcgan, generative-adversarial-network, deep-learning, image-generation, image-manipulation, image-to-image-translation
Last push: 2021-06-06T12:09:47+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": 3577, "days_push": 1914, "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 10652, forks 1731 (observed 2026-08-28T04:10:43.669483+00:00)

## What it is
The original Torch (Lua) implementation of pix2pix, a conditional GAN for image-to-image translation tasks such as synthesizing photos from label maps, colorization, and edge-to-photo reconstruction. It is the research code for the CVPR 2017 paper, with the authors recommending the actively maintained PyTorch port instead.

## Use cases
- translate images from one domain to another with a conditional GAN
- generate building facades from label maps
- colorize black-and-white images
- reconstruct photos from edge maps
- train an image-to-image translation model on a custom paired dataset
- reproduce the pix2pix CVPR 2017 paper results

## When to choose
- you need the original Torch implementation for research reproduction or comparison
- you have paired image datasets and an NVIDIA GPU for training
- you want to study the reference implementation of conditional adversarial image translation

## When to avoid
- you want an actively maintained framework - use the PyTorch port instead
- your environment does not support the deprecated Torch/Lua ecosystem
- you need CPU-only training at scale or production deployment

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, image-processing, machine-learning
- platform: lua
- tags: gan, pix2pix, image-to-image-translation, torch, generative-adversarial-network, research-code, image-generation, linux, macos, gpu

## Member repositories
- phillipi/pix2pix (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:43.669483+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 2026-08-29T17:18:13.257256+00:00, confidence not recorded.
  - readme: https://github.com/phillipi/pix2pix (fetched 2026-08-28T04:10:43.669483+00:00, sha f9aa71347b35)
  - homepage: https://phillipi.github.io/pix2pix/ (fetched 2026-08-29T08:17:19.307585+00:00, sha 60e526281694)
- Data as of 2026-08-30T08:39:29.467469+00:00.