# Flode-Labs/vid2densepose

Convert your videos to densepose and use it on MagicAnimate

Repository: https://github.com/Flode-Labs/vid2densepose
Canonical: https://ross.abutalabs.com/products/vid2densepose
Language: Python
License: MIT
License Family: permissive
Topics: densepose, magic-animate
Last push: 2023-12-10T06:40:37+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 71
- inputs: {"age_days": 1002, "days_push": 997, "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 1102, forks 133 (observed 2026-08-28T04:03:35.775309+00:00)

## What it is
A Python tool that applies the DensePose model to videos, producing color-coded part-index visualizations for each frame. Its output is designed to feed into MagicAnimate for temporally consistent human image animation.

## Use cases
- convert videos to densepose format
- generate densepose visualizations from video frames
- prepare inputs for MagicAnimate human animation
- extract body pose maps from video footage
- run densepose estimation on a video via CLI
- use a gradio interface to convert video to densepose

## When to choose
- you need densepose videos specifically for MagicAnimate workflows
- you want a simple CLI or Gradio wrapper around DensePose for video input
- you have a CUDA-capable GPU and want quick pose-map extraction

## When to avoid
- you need real-time pose estimation
- you need general-purpose pose keypoints rather than dense UV maps
- you cannot install Detectron2 or lack GPU support
- you need actively developed tooling with frequent updates

## Facets
- artifact type: cli-tool
- maturity: maintenance
- function: computer-vision, video-processing, image-processing, machine-learning
- domain: computer-vision, machine-learning, artificial-intelligence
- platform: python
- tags: densepose, detectron2, magic-animate, gradio, pose-estimation, human-animation, video, linux, macos, gpu

## Member repositories
- Flode-Labs/vid2densepose (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:35.775309+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 2026-08-30T06:45:35.409945+00:00, confidence not recorded.
  - readme: https://github.com/Flode-Labs/vid2densepose (fetched 2026-08-28T04:03:35.775309+00:00, sha 67aa9e5c8ee9)
- Data as of 2026-08-30T08:39:29.467469+00:00.