# aigc3d/LAM

[SIGGRAPH 2025] LAM: Large Avatar Model for One-shot Animatable Gaussian Head

Repository: https://github.com/aigc3d/LAM
Canonical: https://ross.abutalabs.com/products/lam
Homepage: https://aigc3d.github.io/projects/LAM/
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-06-10T12:12:22+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 86, release rhythm 35, longevity 37
- inputs: {"age_days": 518, "days_push": 84, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1043, forks 105 (observed 2026-08-28T04:03:20.948998+00:00)

## What it is
LAM is a PyTorch implementation of a Large Avatar Model that reconstructs an animatable 3D Gaussian head from a single image in one forward pass. It enables real-time animation and rendering across platforms, including mobile and WebGL, and integrates with OpenAvatarChat for interactive 3D chatting avatars.

## Use cases
- create a 3D talking avatar from one photo
- animate a gaussian head avatar with audio input
- render 3D avatars in real time in the browser with WebGL
- build an interactive 3D digital human chatbot
- export avatars for OpenAvatarChat
- reenact a face from a single image

## When to choose
- you need a photorealistic animatable 3D head from a single image
- you want real-time avatar rendering on mobile or web
- you are building an interactive 3D chatting avatar pipeline

## When to avoid
- you need full-body avatars rather than heads
- you lack a GPU for inference
- you need offline video-based avatar training from captured sequences

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, graphics, sdk, tts
- domain: artificial-intelligence, computer-vision, graphics, chatbots, large-language-models
- platform: python, cross-platform
- tags: gaussian-splatting, 3d-avatar, face-reconstruction, flame, digital-human, one-shot, siggraph, talking-head, webgl, gpu, web, docker

## Member repositories
- aigc3d/LAM (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.948998+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:02:29.263908+00:00, confidence not recorded.
  - readme: https://github.com/aigc3d/LAM (fetched 2026-08-28T04:03:20.948998+00:00, sha 6b1d7b9c3d6b)
  - homepage: https://aigc3d.github.io/projects/LAM/ (fetched 2026-08-29T13:03:40.682882+00:00, sha 8a17083e14b2)
- Data as of 2026-08-30T08:39:29.467469+00:00.