# mayuelala/FollowYourPose

[AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"

Repository: https://github.com/mayuelala/FollowYourPose
Canonical: https://ross.abutalabs.com/products/followyourpose
Homepage: https://follow-your-pose.github.io/
Language: Python
License: MIT
License Family: permissive
Topics: aaai-2024, aigc, video-generation, follow-your-pose, laion-pose-dataset
Last push: 2024-03-20T01:44:18+00:00

## Health v2 (maintenance only)
Score: 21/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 89
- inputs: {"age_days": 1252, "days_push": 897, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1358, forks 96 (observed 2026-08-28T04:04:29.639867+00:00)

## What it is
Official PyTorch implementation of Follow-Your-Pose (AAAI 2024), a pose-guided text-to-video generation model that tunes a text-to-image model like Stable Diffusion to generate character videos from pose sequences and text descriptions. It trains on pose-free videos and supports text-editable, pose-controllable video synthesis.

## Use cases
- generate character videos from pose sequences and text prompts
- create pose-controllable digital human animations
- restyle a reference motion video with a text description
- generate cartoon or stylized dancing videos from skeleton poses
- research text-to-video diffusion model tuning
- animate a character in a given style following a pose video

## When to choose
- you need pose-guided text-to-video generation with editable text prompts
- you want a research baseline or official implementation of the AAAI 2024 paper
- you have pose sequences (e.g., from OpenPose) and want to synthesize stylized character videos
- you want to fine-tune or extend a Stable Diffusion-based video generation model

## When to avoid
- you need production-grade, high-resolution, long-duration video generation
- you have no GPU available, as inference and training are compute-heavy
- you want a polished end-user application rather than research code
- you need real-time video generation

## Facets
- artifact type: library
- maturity: maintenance
- function: video-processing, machine-learning, deep-learning, stable-diffusion, image-processing
- domain: deep-learning, computer-vision, artificial-intelligence, image-processing
- platform: python
- tags: text-to-video, pose-guided-generation, diffusion-models, aigc, research-code, aaai-2024, character-animation, video, gpu, linux

## Member repositories
- mayuelala/FollowYourPose (main) score 21

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:29.639867+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 2026-08-30T04:41:46.586410+00:00, confidence not recorded.
  - readme: https://github.com/mayuelala/FollowYourPose (fetched 2026-08-28T04:04:29.639867+00:00, sha 4b1054506e0b)
  - homepage: https://follow-your-pose.github.io/ (fetched 2026-08-29T11:59:49.524089+00:00, sha f79273421a29)
- Data as of 2026-08-30T08:39:29.467469+00:00.