IDEA-Research/HumanSD

[ICCV 2023] The official implementation of paper "HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation"

39
/ 100
Emerging

This project helps graphic designers, artists, and marketers create realistic and stylized images of people with precise control over their poses. You input a text description (like "oil painting of girls dancing") and a skeleton image defining the desired pose. The output is a high-quality human image that accurately matches both the text description and the specific body posture you provided.

306 stars. No commits in the last 6 months.

Use this if you need to generate images of people in specific, complex poses for artistic projects, marketing materials, or visual content creation.

Not ideal if you need to generate images without specific human poses or if your primary focus is on editing existing images rather than generating new ones.

digital-art illustration character-design visual-marketing content-creation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

306

Forks

22

Language

Python

License

Apache-2.0

Last pushed

Oct 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/IDEA-Research/HumanSD"

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