akanimax/BMSG-GAN
[MSG-GAN] Any body can GAN! Highly stable and robust architecture. Requires little to no hyperparameter tuning. Pytorch Implementation
This project helps machine learning practitioners generate high-quality, realistic images from scratch, even at large sizes like 1024x1024. You provide a dataset of images, and it outputs a model capable of producing new, diverse images that look like they belong to your original dataset. This is ideal for researchers or developers working on image synthesis and generation tasks.
627 stars. No commits in the last 6 months.
Use this if you need a stable and robust way to train Generative Adversarial Networks (GANs) for synthesizing high-resolution images with minimal hyperparameter tuning.
Not ideal if you are looking for the official research paper's implementation of MSG-GAN, as this is a separate PyTorch implementation.
Stars
627
Forks
103
Language
Python
License
MIT
Category
Last pushed
Jun 17, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/akanimax/BMSG-GAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
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...