akanimax/fagan

A variant of the Self Attention GAN named: FAGAN (Full Attention GAN)

45
/ 100
Emerging

This project helps machine learning engineers and researchers create realistic synthetic images, particularly human faces. By training the system on existing image datasets, it can generate new, unique images that resemble the training data. This is useful for expanding datasets, testing models, or exploring novel image generation techniques.

114 stars. No commits in the last 6 months.

Use this if you need to generate high-quality, diverse synthetic images, such as faces, from a trained model.

Not ideal if you are looking for an out-of-the-box solution for general image manipulation or editing, as it requires training and fine-tuning.

synthetic-data-generation computer-vision deep-learning-research image-synthesis generative-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

114

Forks

31

Language

Python

License

MIT

Last pushed

Nov 21, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/akanimax/fagan"

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