tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
This project helps graphic designers, digital artists, and content creators generate diverse image variations, animate still pictures, or seamlessly blend elements into existing images. You input a single reference image, and it outputs new images that capture the original's style, texture, and structure, or animations that bring static scenes to life. It's ideal for those needing to expand a visual library or manipulate images without extensive manual editing.
443 stars. No commits in the last 6 months.
Use this if you need to create multiple artistic variations from just one image, animate a static scene, or seamlessly integrate new elements into an existing image while maintaining visual consistency.
Not ideal if you need to generate images from text descriptions, combine multiple distinct image styles, or perform complex object-level image manipulations like object removal or replacement.
Stars
443
Forks
77
Language
Python
License
MIT
Category
Last pushed
Jan 13, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tohinz/ConSinGAN"
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...
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017
weihaox/awesome-image-translation
Collection of awesome resources on image-to-image translation.