sagiebenaim/OneShotTranslation

Pytorch implementation of "One-Shot Unsupervised Cross Domain Translation" NIPS 2018

41
/ 100
Emerging

This project helps graphic designers, artists, and researchers rapidly transform the style of images. You provide a collection of images in one style (e.g., photos of real-world objects) and a single example image in a target style (e.g., a hand-drawn sketch), and it outputs your original images redrawn in the target style. It's ideal for visual creatives and researchers exploring artistic effects or data augmentation.

141 stars. No commits in the last 6 months.

Use this if you need to translate an entire dataset of images into a new visual style, especially when you only have one example of the target style.

Not ideal if you need pixel-perfect, highly accurate image-to-image translation for tasks like medical imaging or autonomous driving.

graphic-design style-transfer image-synthesis digital-art visual-effects
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

141

Forks

17

Language

Python

License

Last pushed

Apr 06, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sagiebenaim/OneShotTranslation"

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