# TencentARC/MotionCtrl

Official Code for MotionCtrl [SIGGRAPH 2024]

Repository: https://github.com/TencentARC/MotionCtrl
Canonical: https://ross.abutalabs.com/products/motionctrl
Homepage: https://wzhouxiff.github.io/projects/MotionCtrl/
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-02-19T08:48:54+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 7, release rhythm 35, longevity 71
- inputs: {"age_days": 1001, "days_push": 560, "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 1500, forks 84 (observed 2026-08-28T04:04:54.223676+00:00)

## What it is
MotionCtrl is the official implementation of a SIGGRAPH 2024 paper providing a unified and flexible motion controller for video generation models. It independently controls camera motion and object motion in generated videos and can be deployed on VideoCrafter, AnimateDiff, and Stable Video Diffusion.

## Use cases
- control camera motion in AI-generated videos
- control object motion trajectories in video generation
- add motion control to Stable Video Diffusion
- add motion control to AnimateDiff
- generate videos with specified camera poses
- research code for controllable video generation

## When to choose
- you need fine-grained camera and object motion control over video diffusion models
- you are building on VideoCrafter, AnimateDiff, or SVD and want motion conditioning
- you want to reproduce or extend the MotionCtrl research

## When to avoid
- you need general-purpose video editing rather than motion control
- you lack GPU resources for running video diffusion models
- you need a production video generation pipeline rather than research code

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, llm-inference, llm-training
- domain: deep-learning, computer-vision, artificial-intelligence
- platform: python
- tags: video-generation, camera-motion-control, object-motion, diffusion-models, svd, animatediff, videocrafter, siggraph-2024, research-code, gradio-demo, video, gpu, linux

## Member repositories
- TencentARC/MotionCtrl (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.223676+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 2026-08-30T04:32:58.997145+00:00, confidence not recorded.
  - readme: https://github.com/TencentARC/MotionCtrl (fetched 2026-08-28T04:04:54.223676+00:00, sha 8d97a133168f)
  - homepage: https://wzhouxiff.github.io/projects/MotionCtrl/ (fetched 2026-08-29T11:37:56.578118+00:00, sha 75c05948d00b)
- Data as of 2026-08-30T08:39:29.467469+00:00.