cryu854/SinGAN
"SinGAN : Learning a Generative Model from a Single Natural Image" in TensorFlow 2
This tool helps graphic designers, digital artists, and photographers create diverse and realistic new images directly from a single example image. You provide one natural image, and the system generates a variety of new images that look similar but have novel shapes and structures, maintaining the original's visual style. It's also great for editing, harmonizing elements, or turning rough sketches into realistic images.
No commits in the last 6 months.
Use this if you need to generate new, original visual content or manipulate existing images with a cohesive style, all based on just one source image.
Not ideal if you require precise control over every pixel or if you need to generate images from text descriptions or large datasets.
Stars
17
Forks
7
Language
Python
License
—
Category
Last pushed
Oct 09, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/cryu854/SinGAN"
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