theopfr/cycle-gan-pytorch

This repository contains an implementation of the Cylce-GAN architecture for style transfer along with instructions to train on an own dataset.

20
/ 100
Experimental

This tool helps researchers and artists transform images from one visual style or domain to another without needing paired examples. You provide two collections of images, each representing a distinct style (e.g., photos of horses and photos of zebras). The tool then learns to translate images between these styles, outputting new images that look like they belong to the target style. This is ideal for those in fields like digital art, research in computer vision, or creative media.

No commits in the last 6 months.

Use this if you need to convert a collection of images from one visual style or domain to another, and you don't have exact 'before and after' pairs for training.

Not ideal if you need precise, pixel-for-pixel transformations or if the distinct visual styles you're working with are too subtle or abstract.

image-style-transfer digital-art visual-effects computer-vision-research synthetic-data-generation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Python

License

Last pushed

Mar 21, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/theopfr/cycle-gan-pytorch"

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