ZPdesu/SEAN
SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)
This project helps graphic designers, digital artists, and researchers easily edit and generate realistic images, especially faces. You provide a segmentation mask (outlining regions like hair, skin, eyes) and reference style images, and it outputs a new image where the style of each region is precisely controlled. It's for anyone needing advanced, region-specific style transfer and interactive image manipulation.
658 stars. No commits in the last 6 months.
Use this if you need to precisely control the visual style of individual semantic regions within an image, such as changing the hair color or texture on a face independently from the eyes or skin.
Not ideal if you're looking for a simple, one-click photo filter or if you don't need fine-grained control over specific image regions.
Stars
658
Forks
92
Language
Python
License
—
Category
Last pushed
Jun 02, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ZPdesu/SEAN"
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