xiyichen/morphablediffusion

[CVPR 2024] Official implementation of Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation

37
/ 100
Emerging

This tool helps 3D artists, game developers, or animators create realistic, 3D-consistent digital avatars from a single 2D image. You input one image of a person's face or body and another image showing the desired facial expression. The output is a series of images of the avatar with the new expression, along with data to reconstruct a 3D mesh.

104 stars. No commits in the last 6 months.

Use this if you need to generate 3D-consistent views of a human avatar, particularly for animating facial expressions, starting from just one photograph.

Not ideal if you need full 3D mesh reconstruction directly without an additional step, or if your primary goal is not avatar creation or animation.

3D-avatar-creation digital-humans facial-animation game-development virtual-reality-content
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

104

Forks

10

Language

Python

License

MIT

Last pushed

Mar 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/xiyichen/morphablediffusion"

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