silence-tang/GaussianIP

[CVPR 2025] Official Implementation of GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior

29
/ 100
Experimental

This project helps 3D artists and content creators quickly generate highly realistic 3D human models. You provide a text description and an image prompt, and it outputs a detailed 3D human model that faithfully preserves the identity from your image, including fine facial features and clothing details. This is for professionals who need to create custom, lifelike 3D human characters efficiently.

No commits in the last 6 months.

Use this if you need to generate high-quality, identity-preserving 3D human models from a single image and text description, with significantly faster processing times than traditional methods.

Not ideal if you require generating non-human 3D objects or already have detailed 3D scans that just need minor adjustments.

3D-character-design digital-avatar-creation CGI game-development virtual-fashion
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

25

Forks

1

Language

Python

License

MIT

Last pushed

Aug 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/silence-tang/GaussianIP"

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