VinAIResearch/QC-StyleGAN
QC-StyleGAN - Quality Controllable Image Generation and Manipulation (NeurIPS 2022)
This project helps graphic designers, digital artists, and marketing professionals generate and manipulate images with precise control over their visual quality. It takes existing images, even low-quality ones, and can either enhance them to a sharp, clear version or introduce controlled degradations like blur, noise, or compression artifacts. The output is a new image tailored to the desired quality level.
No commits in the last 6 months.
Use this if you need to generate high-quality images from scratch, modify existing images while maintaining or changing their quality, or simulate various image degradations for testing or creative purposes.
Not ideal if you're looking for a simple photo editor for casual use without needing advanced control over image generation parameters or training custom models.
Stars
26
Forks
1
Language
Python
License
AGPL-3.0
Category
Last pushed
Jul 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/VinAIResearch/QC-StyleGAN"
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