bryandlee/stylegan2-encoder-pytorch
PyTorch Implementation of In-Domain GAN Inversion for StyleGAN2
This tool helps creative professionals or researchers modify specific features of real-world portrait photos, like a person's age, expression, or hair color, to create realistic new images. You provide an existing image, and it outputs a new version with controlled alterations, without distorting the original subject. It's designed for users who need precise, natural-looking image manipulations for creative or experimental purposes.
151 stars. No commits in the last 6 months.
Use this if you need to take a real photograph of a face and subtly or dramatically change its features in a way that looks completely natural and retains the original subject's identity.
Not ideal if you only need basic photo adjustments or cartoon-style filters, or if you're not comfortable with a technical setup.
Stars
151
Forks
23
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 09, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bryandlee/stylegan2-encoder-pytorch"
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