Ha0Tang/C2GAN
[ACM MM 2019 Oral] Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
This project helps researchers and artists create new images based on specific human poses or facial expressions. You provide an input image with keypoints (like joint positions or facial landmarks) and the system generates a new, realistic image that matches those keypoints. It's designed for those working in computer graphics, animation, or visual effects who need to synthesize controlled human imagery.
No commits in the last 6 months.
Use this if you need to generate realistic images of people, animals, or objects with precise control over their pose or expression using keypoint guidance.
Not ideal if you need a tool for general image editing, style transfer without keypoint control, or generating entirely novel scenes from scratch.
Stars
70
Forks
5
Language
Python
License
—
Category
Last pushed
Feb 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Ha0Tang/C2GAN"
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