EndlessSora/TSIT
[ECCV 2020 Spotlight] A Simple and Versatile Framework for Image-to-Image Translation
This project helps graphic designers, digital artists, or urban planners transform the style or characteristics of an image. You input an image, and it outputs a new image where the visual style or semantic elements have been altered. For example, it can change a summer photo to look like winter, or a daytime scene to nighttime.
285 stars. No commits in the last 6 months.
Use this if you need to quickly generate variations of existing images by applying different styles, creating semantic changes like altering weather conditions, or synthesizing new images from semantic layouts without needing to manually draw or recolor.
Not ideal if you're looking for photo editing tools that involve precise object manipulation, retouching, or color grading, as this focuses on broader image-to-image transformations.
Stars
285
Forks
34
Language
Python
License
—
Category
Last pushed
Jul 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/EndlessSora/TSIT"
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