UniBester/AGE

A implementation of Attribute Group Editing for Reliable Few-shot Image Generation (CVPR 2022)

36
/ 100
Emerging

This project helps visual content creators and researchers generate diverse, realistic images for categories with very limited examples. You provide a few images of a new object or animal, and the system can create many more variations, even without extensive retraining. It's designed for anyone needing to expand visual datasets for underrepresented subjects.

No commits in the last 6 months.

Use this if you need to generate high-quality, varied images for subjects where you only have a handful of existing pictures, like rare animal species, specific product variants, or unique facial expressions.

Not ideal if you already have large datasets for your image categories or if you need to generate images from scratch without any existing examples.

image generation visual content creation dataset augmentation computer vision research few-shot learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

59

Forks

7

Language

Python

License

MIT

Last pushed

Apr 12, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/UniBester/AGE"

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