# Francis-Rings/StableAnimator

[CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.

Repository: https://github.com/Francis-Rings/StableAnimator
Canonical: https://ross.abutalabs.com/products/stableanimator
Language: Python
License: MIT
License Family: permissive
Last push: 2025-09-21T01:52:23+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 43, release rhythm 35, longevity 46
- inputs: {"age_days": 645, "days_push": 347, "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 1430, forks 102 (observed 2026-08-28T04:04:42.302659+00:00)

## What it is
StableAnimator is an end-to-end ID-preserving video diffusion framework that animates a reference human image according to a sequence of poses, producing high-fidelity videos without face post-processing. It is a Python research codebase released at CVPR 2025, built on a video diffusion model with identity-consistency modules.

## Use cases
- animate a photo with a pose sequence
- generate identity-preserving talking or dancing videos from an image
- create human image animation without face swapping post-processing
- run pose-driven video generation on a reference portrait
- research video diffusion identity consistency

## When to choose
- you need high-fidelity ID-preserving human animation from a single image and pose sequence
- you want to avoid separate face-swap or face-restoration post-processing
- you have a GPU and want a state-of-the-art research model

## When to avoid
- you need lightweight or CPU-only video generation
- you want general text-to-video rather than pose-conditioned human animation
- you lack GPU resources for diffusion inference

## Facets
- artifact type: library
- maturity: active
- function: video-processing, image-processing, deep-learning, stable-diffusion, machine-learning
- domain: computer-vision, deep-learning, image-processing, artificial-intelligence
- platform: python
- tags: video-diffusion, human-image-animation, identity-preservation, pose-driven, cvpr2025, face-consistency, video, gpu, linux

## Member repositories
- Francis-Rings/StableAnimator (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:42.302659+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 2026-08-30T04:37:10.365216+00:00, confidence not recorded.
  - readme: https://github.com/Francis-Rings/StableAnimator (fetched 2026-08-28T04:04:42.302659+00:00, sha b48d66fe0fcd)
- Data as of 2026-08-30T08:39:29.467469+00:00.