NVlabs/MUNIT

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

2707 stars · 487 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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 The repository is no longer maintained; NVIDIA points users to the improved implementation in the imaginaire project.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

library · maturity abandoned

image-processing machine-learning deep-learning computer-vision image-processing deep-learning machine-learning python gan image-translation pix2pix munit unsupervised-learning research-code nvidia linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="NVlabs/MUNIT")