nicolas-dufour/SCAM

Code for SCAM! Transferring humans between images with Semantic Cross Attention Modulation. Also contains implementation for SPADE, CLADE, SEAN and INADE

19
/ 100
Experimental

This project allows you to digitally transfer a human figure from one image into a completely different background image, while realistically adapting their appearance. You provide an image of a person and a separate image of a desired scene, and it generates a new image with the person seamlessly integrated into the new environment. This tool would be used by researchers in computer vision, graphics, or image synthesis who are exploring advanced image manipulation and human-centric content generation.

No commits in the last 6 months.

Use this if you need to realistically place human subjects from one photo into diverse new backgrounds for research or experimental image generation.

Not ideal if you are looking for a simple, user-friendly application for everyday photo editing, as it requires programming knowledge and specific data preparation.

Image Synthesis Computer Graphics Research Human Pose Transfer Vision AI Development Content Generation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 3 / 25

How are scores calculated?

Stars

56

Forks

1

Language

Python

License

Last pushed

Nov 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nicolas-dufour/SCAM"

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