SHI-Labs/StyleNAT

New flexible and efficient image generation framework that sets new SOTA on FFHQ-256 with FID 2.05, 2022

41
/ 100
Emerging

This is a framework for generating high-quality, realistic images, specifically of human faces and churches, with superior efficiency. You input training datasets of images, and it outputs a model capable of generating new, unique images that match the style and characteristics of the training data. This tool is for researchers and practitioners in computer vision or digital content creation who need to synthesize high-fidelity visual content.

102 stars. No commits in the last 6 months.

Use this if you need to generate high-resolution, photorealistic images from scratch, particularly for datasets like human faces or architectural structures, with a focus on efficiency and quality.

Not ideal if you're looking for a simple, out-of-the-box image editor or a tool for generating images based on text prompts rather than learned styles.

image-synthesis generative-art computer-vision-research digital-content-creation deep-learning-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

102

Forks

13

Language

Python

License

MIT

Category

gan-based-t2i

Last pushed

Jun 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/SHI-Labs/StyleNAT"

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