NVlabs/MUNIT

Multimodal Unsupervised Image-to-Image Translation

50
/ 100
Established

This project helps graphic designers, digital artists, or researchers transform images from one visual domain to another, even when there isn't a direct pairing between the original and desired styles. For example, you can input a summer landscape and get a winter version, or turn a drawing of edges into a realistic shoe photo. This is useful for anyone needing to generate diverse visual content or explore different stylistic representations of existing images.

2,703 stars. No commits in the last 6 months.

Use this if you need to translate images between distinct visual categories without having perfectly matched examples for training, like converting photos of horses to zebras or transforming a city street scene to a different artistic style.

Not ideal if you require precise, pixel-for-pixel transformations or if you are working with non-image data.

digital-art visual-content-creation image-stylization generative-design photo-editing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

2,703

Forks

483

Language

Python

License

Last pushed

Sep 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVlabs/MUNIT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Compare