ali-vilab/UniAnimate

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1189 stars · 62 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

UniAnimate is the official code for a research paper on animating a reference human image into a video that follows a driving pose sequence, using unified video diffusion models. It supports long-term video generation (up to about a minute) via first-frame conditioning and a state-space-model temporal architecture.

Use cases

• animate a photo of a person with a driving pose sequence
• generate dance videos from a reference image
• create long consistent human animation videos
• research on video diffusion models for human animation
• pose-driven character video synthesis

When to choose

• you need research-grade human image animation with pose control
• you want to generate long videos of a person from a single image
• you have a GPU and want to experiment with video diffusion models

When to avoid

• you need a production-ready product with a polished UI
• you have no GPU available
• you need a permissively licensed library for commercial use (no license is provided)

Facets

library · maturity active

video-processing deep-learning image-processing machine-learning computer-vision deep-learning artificial-intelligence python human-image-animation video-diffusion pose-driven-animation dance-generation video-generation research-code video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ali-vilab/UniAnimate")