yunqing-me/AdAM

[NeurIPS-2022] Annual Conference on Neural Information Processing Systems

27
/ 100
Experimental

This tool helps researchers and content creators generate new, high-quality images for specific subjects or styles, even when they only have a handful of example images. By taking a pre-existing image generation model (like one trained on general human faces) and a small set of target images (e.g., ten images of babies), it can create new images that perfectly match the target's unique characteristics. This is ideal for those needing to quickly expand a small image dataset or create variations of niche visual content.

No commits in the last 6 months.

Use this if you need to generate many diverse images that adhere to a very specific visual style or subject, but only have a few reference images available.

Not ideal if you're looking for a simple, off-the-shelf image generator that doesn't require fine-tuning with your own data or if you have a large dataset already.

generative AI image synthesis data augmentation content creation visual research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

19

Forks

1

Language

Python

License

MIT

Last pushed

Dec 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/yunqing-me/AdAM"

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