ankanbhunia/PIDM

Person Image Synthesis via Denoising Diffusion Model (CVPR 2023)

44
/ 100
Emerging

This project helps fashion designers, advertisers, or creative professionals generate realistic images of people in different poses or outfits. You provide an input image of a person and desired poses (or a reference image for styling), and it creates new images of that person adopting the new poses or apparel. This is ideal for quickly visualizing how clothing looks on various models without costly photoshoots.

500 stars. No commits in the last 6 months.

Use this if you need to generate new, high-quality images of people, either by changing their pose or their clothing appearance, from an existing image.

Not ideal if you need to generate images of entirely new people or objects from scratch, or if your primary focus is on editing specific features rather than full-body transformations.

fashion-design advertising-creative virtual-try-on image-synthesis visual-merchandising
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

500

Forks

61

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 11, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ankanbhunia/PIDM"

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