#10 · Primary category： 3D Generation & Asset Creation
LHM
[ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
Project last updated：03/17/26
GitHub Stars
2.7K
Forks
213
Contributors
4
License
Apache-2.0
Why we included this project
Feed LHM a single photo and it returns an animatable 3D human in seconds, which makes it a genuinely practical open option for teams working on avatars, virtual production, or game characters. It's an ICCV 2025 paper from Alibaba's Tongyi Lab, and the reconstructed body is riggable: you can drive it with either extracted or external motion sequences, so the output is a working digital double rather than a static mesh. The repo includes inference code, pretrained weights in several sizes, and a MINI variant tuned to run on 16 GB GPUs, plus ComfyUI integration, so you can experiment without standing up a research pipeline yourself. If you need characters for games, pre-vis, or synthetic training data, it's worth testing against your own quality and hardware limits.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
modly
Desktop app to generate 3D models from images or prompt using local AI — runs entirely on your GPU
LichtFeld-Studio
Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.
map-anything
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
ComfyUI-3D-Pack
An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)
dust3d
Dust3D is a cross-platform 3D modeling software that makes it easy to create low poly 3D models for video games, 3D printing, and more.