# guoqincode/Open-AnimateAnyone

Unofficial Implementation of Animate Anyone

Repository: https://github.com/guoqincode/Open-AnimateAnyone
Canonical: https://ross.abutalabs.com/products/open-animateanyone
Language: Python
License Family: other
Last push: 2024-07-09T16:58:35+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 71
- inputs: {"age_days": 1000, "days_push": 785, "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 2923, forks 238 (observed 2026-08-28T04:07:30.274480+00:00)

## What it is
An unofficial PyTorch implementation of Animate Anyone, a diffusion-based method that animates a static character image using pose sequences. It includes training guidance and models trained on small datasets like TikTok and UBC-fashion.

## Use cases
- animate a character image from a pose video
- generate character animation videos from skeleton poses
- reproduce Animate Anyone research results
- train a pose-driven character animation model
- create virtual try-on or dance animation videos

## When to choose
- you want an open-source starting point for pose-driven character animation
- you want to study or extend the Animate Anyone architecture
- you have your own large high-quality video dataset to train with

## When to avoid
- you need production-quality animation matching the official Animate Anyone results
- you cannot train on large-scale data since small-data training produces artifacts and flicker
- you need a commercially licensed project (no license is provided)

## Facets
- artifact type: library
- maturity: experimental
- function: image-processing, video-processing, deep-learning, machine-learning
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python
- tags: character-animation, pose-driven-animation, diffusion-models, unofficial-implementation, video-generation, video, linux, gpu

## Member repositories
- guoqincode/Open-AnimateAnyone (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.274480+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 2026-08-30T07:33:44.850436+00:00, confidence not recorded.
  - readme: https://github.com/guoqincode/Open-AnimateAnyone (fetched 2026-08-28T04:07:30.274480+00:00, sha cb96928003fc)
- Data as of 2026-08-30T08:39:29.467469+00:00.