# hongfz16/AvatarCLIP

[SIGGRAPH 2022 Journal Track] AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars

Repository: https://github.com/hongfz16/AvatarCLIP
Canonical: https://ross.abutalabs.com/products/avatarclip
Homepage: https://hongfz16.github.io/projects/AvatarCLIP.html
Language: Python
License: NOASSERTION
License Family: other
Topics: 3d-generation, nerf, motion-generation
Last push: 2023-02-15T12:46:00+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1583, "days_push": 1295, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1100, forks 99 (observed 2026-08-28T04:03:35.362400+00:00)

## What it is
Official PyTorch implementation of AvatarCLIP, a SIGGRAPH 2022 research framework that generates and animates 3D human avatars from natural-language descriptions of body shape, appearance, and motion. It uses CLIP to supervise neural human geometry, texture generation via volume rendering, and CLIP-guided motion synthesis with motion VAE priors.

## Use cases
- generate a 3D avatar from a text description
- animate a 3D character with a text-described motion
- create stylized 3D humans without modeling software
- text-driven 3D human shape and texture generation
- research baseline for zero-shot avatar generation
- produce animated avatar clips for demos

## When to choose
- you want to generate 3D avatars purely from natural language
- you need a research reference implementation of CLIP-guided 3D human generation
- you have a GPU environment and want to reproduce SIGGRAPH 2022 results

## When to avoid
- you need production-ready avatar tooling with a polished UI
- you lack a CUDA GPU or the SMPL body model assets
- you need a permissively licensed codebase for commercial use

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, graphics, simulation, nlp
- domain: computer-vision, graphics, artificial-intelligence
- platform: python
- tags: 3d-avatars, clip, text-to-3d, neural-rendering, motion-generation, research-code, siggraph, natural-language-processing, gpu, linux

## Member repositories
- hongfz16/AvatarCLIP (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:35.362400+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 2026-08-30T06:45:48.042750+00:00, confidence not recorded.
  - readme: https://github.com/hongfz16/AvatarCLIP (fetched 2026-08-28T04:03:35.362400+00:00, sha e103cb2283b3)
  - homepage: https://hongfz16.github.io/projects/AvatarCLIP.html (fetched 2026-08-29T12:49:16.743807+00:00, sha 3ef84888edb5)
- Data as of 2026-08-30T08:39:29.467469+00:00.