microsoft/CoCosNet-v2

CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation

42
/ 100
Emerging

This project helps fashion designers and e-commerce retailers create new clothing images by transferring styles or outfits from one reference photo to another, even with different body poses. You provide an input image (like a person in a specific pose) and a reference image (like an outfit you want to apply). The system then generates a new, high-resolution image of the input person wearing the reference outfit, matching the original pose.

345 stars. No commits in the last 6 months.

Use this if you need to generate high-quality, realistic images of clothing on various models or poses for fashion design, virtual try-on, or e-commerce catalog creation.

Not ideal if your primary goal is general image manipulation or editing where precise semantic correspondence between distinct image domains isn't the main challenge.

fashion-design e-commerce image-synthesis virtual-try-on apparel-imaging
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

345

Forks

35

Language

Python

License

MIT

Category

image-inpainting

Last pushed

Jul 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/CoCosNet-v2"

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