tatsuyah/CycleGAN-Models
Models generated by CycleGAN
This collection provides pre-trained models that can transform the appearance of subjects in images without needing paired examples. For instance, you could input an image of a bear and get an image of a panda, or transform a person's facial features to resemble Spock. This is for digital artists, content creators, or researchers experimenting with creative visual transformations.
No commits in the last 6 months.
Use this if you want to visually change subjects in images, like turning a horse into a zebra or a man into Spock, using existing models.
Not ideal if you need to train a custom image transformation model from scratch or require precise, photorealistic alterations for commercial use.
Stars
43
Forks
5
Language
—
License
MIT
Category
Last pushed
Sep 10, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tatsuyah/CycleGAN-Models"
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