Ha0Tang/XingGAN
[ECCV 2020] XingGAN for Person Image Generation
This tool helps researchers and designers in computer vision and fashion generate realistic images of people by transferring poses from one person to another. You input a source image of a person and a target image or pose, and it generates a new image of the person from the source in the pose of the target. This is ideal for those working on virtual try-on, character animation, or generating diverse image datasets.
225 stars. No commits in the last 6 months.
Use this if you need to create new images of people in specific poses, such as changing an outfit on a model or animating a character's stance.
Not ideal if you need to generate images of non-human subjects or require detailed control over facial expressions or background changes.
Stars
225
Forks
36
Language
Python
License
—
Category
Last pushed
Feb 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Ha0Tang/XingGAN"
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