yuanming-hu/exposure
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.
Exposure helps photographers and image editors automatically enhance photos with a unique, artistic touch. You input a raw or high-quality image, and it outputs a post-processed version with improved exposure, color, and tone, mimicking the style of professional edits. This tool is for anyone wanting to quickly apply advanced photo adjustments without manual tweaking.
780 stars. No commits in the last 6 months.
Use this if you want to automate advanced photo post-processing, especially for high-resolution images, and desire varied artistic outcomes from a single input.
Not ideal if you need pixel-perfect, consistent, or highly precise manual control over every editing parameter, or if you primarily work with low-resolution 8-bit JPGs.
Stars
780
Forks
156
Language
Python
License
MIT
Category
Last pushed
Aug 27, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yuanming-hu/exposure"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
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]
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...