# NVlabs/MUNIT

Multimodal Unsupervised Image-to-Image Translation

Repository: https://github.com/NVlabs/MUNIT
Canonical: https://ross.abutalabs.com/products/munit
Language: Python
License: NOASSERTION
License Family: other
Topics: gan, deep-learning, pix2pix, image-translation, munit
Last push: 2022-09-20T12:23:52+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3078, "days_push": 1443, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2707, forks 487 (observed 2026-08-28T04:07:11.609169+00:00)

## What it is
Official PyTorch implementation of MUNIT (ECCV 2018), a GAN-based model for multimodal unsupervised image-to-image translation. The repository is no longer maintained; NVIDIA points users to the improved implementation in the imaginaire project.

## Use cases
- translate images between domains without paired data
- generate multiple plausible outputs from one input image
- convert edges to shoes or handbags
- season transfer like summer to winter photos
- example-guided image translation
- reproduce MUNIT paper experiments

## When to choose
- studying or reproducing the MUNIT ECCV 2018 paper
- research on multimodal unsupervised image translation
- non-commercial academic use with GAN-based translation

## When to avoid
- you need maintained or production-ready code
- commercial use (CC BY-NC-SA 4.0 license)
- you want the improved implementation - use NVlabs/imaginaire instead
- modern Python environments (code targets Python 2.7/3.6)

## Facets
- artifact type: library
- maturity: abandoned
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python
- tags: gan, image-translation, pix2pix, munit, unsupervised-learning, research-code, nvidia, linux, gpu

## Member repositories
- NVlabs/MUNIT (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.609169+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 2026-08-30T02:15:41.905066+00:00, confidence not recorded.
  - readme: https://github.com/NVlabs/MUNIT (fetched 2026-08-28T04:07:11.609169+00:00, sha 06ee99150671)
- Data as of 2026-08-30T08:39:29.467469+00:00.