yinboc/infd

Image Neural Field Diffusion Models, CVPR 2024 (Highlight)

31
/ 100
Emerging

This project helps researchers and practitioners in computer vision generate realistic, high-resolution images. It takes a collection of existing images, such as a dataset of faces, and learns to create entirely new, diverse images that look very similar to the originals but are not exact copies. Computer vision researchers and AI artists would find this useful for expanding datasets or creating novel visual content.

No commits in the last 6 months.

Use this if you need to generate high-fidelity, photorealistic images from scratch based on a given dataset, particularly for research or content creation.

Not ideal if you need to perform image editing, style transfer, or other image manipulations on existing images, rather than generating new ones.

generative AI image synthesis computer vision research digital content creation deep learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

80

Forks

3

Language

Python

License

BSD-3-Clause

Last pushed

Nov 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yinboc/infd"

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