huanngzh/Parts2Whole

[TIP 2025] From Parts to Whole: A Unified Reference Framework for Controllable Human Image Generation

37
/ 100
Emerging

This project helps designers, marketers, and artists create unique human portraits by combining specific body parts and styles from various reference images. You provide separate images for things like a face, a particular outfit, or a pose, along with a text description, and it generates a new, integrated human image. This is ideal for anyone needing to generate customized human images for campaigns, virtual try-ons, or creative content without complex photo editing.

196 stars. No commits in the last 6 months.

Use this if you need to generate high-quality, customized human images by assembling different visual elements like faces, clothing, and poses from multiple sources, controlled by text prompts.

Not ideal if you need to generate images with highly specific artistic styles or if your primary subjects are not human, as the current model's generalization across diverse styles and non-human subjects is limited.

fashion-design digital-art advertising-marketing virtual-try-on content-creation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

196

Forks

9

Language

Python

License

MIT

Last pushed

Sep 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/huanngzh/Parts2Whole"

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