bryandlee/FreezeG
Freezing generator for pseudo image translation
This tool helps creative professionals or researchers transform an input image into a stylistically different, yet recognizable, output image. For instance, you could turn a photo of a person into a cartoon character or change a cat's appearance to a wild animal, retaining the original subject's unique features. It's designed for users who want to experiment with image style transfer while maintaining subject identity.
478 stars. No commits in the last 6 months.
Use this if you need to translate images from one style or domain to another, like converting a human face into an anime style, and are working with existing image datasets.
Not ideal if you need to translate images with large geometric changes, such as transforming a cat into a flower, as the connection between the original and resulting image becomes less intuitive.
Stars
478
Forks
51
Language
Python
License
MIT
Category
Last pushed
Mar 30, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bryandlee/FreezeG"
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