wkentaro/chainer-cyclegan
Chainer implementation of "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Network".
This tool transforms images from one visual style or domain to another without needing paired examples. You provide a collection of images from a source domain (e.g., photos of horses) and another collection from a target domain (e.g., photos of zebras), and it generates new images that look like the target domain while retaining content from the source. It's ideal for artists, designers, or researchers who want to explore visual translations between different image sets.
No commits in the last 6 months. Available on PyPI.
Use this if you need to convert an entire collection of images from one visual style or object type to another, like turning summer landscapes into winter scenes or horses into zebras, without painstakingly matching up individual pictures.
Not ideal if you need pixel-perfect, content-preserving transformations where precise alignment between input and output images is critical, such as medical imaging analysis or architectural drafting.
Stars
10
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 18, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/wkentaro/chainer-cyclegan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
taesungp/contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV...
PaddlePaddle/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion...
tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017