NVIDIA/pix2pixHD
Synthesizing and manipulating 2048x1024 images with conditional GANs
This project helps graphic designers, urban planners, or visual artists transform simple semantic maps into highly realistic images at high resolutions. You input a diagram where different colors or outlines represent objects like roads, buildings, or facial features, and it generates a photorealistic image based on that map. This is useful for quickly visualizing concepts or creating synthetic visual content.
6,974 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to generate detailed, photorealistic images from basic semantic layouts, such as turning a colored map of a city into a lifelike street view or a face diagram into a portrait.
Not ideal if your primary goal is to perform general image enhancement, style transfer between existing photos, or if you don't have clear semantic label maps as your input.
Stars
6,974
Forks
1,416
Language
Python
License
—
Category
Last pushed
Nov 04, 2024
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NVIDIA/pix2pixHD"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related models
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...
yiranran/APDrawingGAN
Code for APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical...