phillipi/pix2pix
Image-to-image translation with conditional adversarial nets
This project helps you automatically transform an image from one visual representation to another, for example, turning a grayscale photo into a color one, or converting a map into a satellite image. You provide pairs of corresponding images (like a sketch and its final product), and the system learns how to make the transformation itself. This is useful for designers, architects, or anyone needing to generate different visual styles or representations from existing images.
10,628 stars. No commits in the last 6 months.
Use this if you need to automatically convert images from one visual style or data type to another, where you have examples of both the input and desired output.
Not ideal if you don't have paired examples of input and output images, or if you're looking to generate entirely new images without a source input.
Stars
10,628
Forks
1,737
Language
Lua
License
—
Category
Last pushed
Jun 06, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/phillipi/pix2pix"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
NVIDIA/pix2pixHD
Synthesizing and manipulating 2048x1024 images with conditional GANs
GaParmar/clean-fid
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
yuanming-hu/exposure
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets,...
albertpumarola/GANimation
GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]
wuhuikai/GP-GAN
Official Chainer implementation of GP-GAN: Towards Realistic High-Resolution Image Blending...