Ha0Tang/BiGraphGAN
[BMVC 2020 Oral] Bipartite Graph Reasoning GANs for Person Image Generation
This project helps fashion designers, advertisers, or researchers create realistic images of people dressed in specific outfits or poses. It takes an image of a person and a separate image of clothing or a target pose as input, then generates a new image of that person wearing the specified clothing or striking the new pose. This is useful for visual content creators who need to quickly generate diverse visual representations of individuals for various purposes.
128 stars. No commits in the last 6 months.
Use this if you need to generate new images of people in different clothes or poses from existing photos, for applications like virtual try-on or character animation.
Not ideal if your goal is to generate images of entirely new, non-existent people or objects, as it focuses on transferring attributes between existing person images.
Stars
128
Forks
16
Language
Python
License
—
Category
Last pushed
Jan 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Ha0Tang/BiGraphGAN"
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