ajbrock/BigGAN-PyTorch

The author's officially unofficial PyTorch BigGAN implementation.

49
/ 100
Emerging

This project helps machine learning researchers or practitioners generate highly realistic images, such as dog breeds or landscapes, from scratch. You provide a dataset of existing images (like ImageNet), and the system learns to create entirely new, high-quality images that match the style and content of your input. It's designed for those working with advanced generative AI models.

2,924 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer looking to train or fine-tune a BigGAN model for high-fidelity image synthesis on substantial datasets using multiple GPUs.

Not ideal if you need a simple, ready-to-use tool for basic image generation without advanced deep learning knowledge or access to powerful multi-GPU hardware.

generative-ai image-synthesis deep-learning-research computer-vision synthetic-data-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

2,924

Forks

484

Language

Python

License

MIT

Last pushed

Jul 19, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ajbrock/BigGAN-PyTorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.