taco-group/Pulse-of-Motion
The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
This tool helps video creators and evaluators understand the true speed of motion in their videos, especially those generated by AI. You input a video file, and it outputs the 'Physical Frames Per Second' (PhyFPS), which reflects the perceived motion speed, rather than just the video's technical frame rate. It's for anyone creating or auditing video content, particularly those working with AI-generated footage.
Use this if you need to objectively measure and ensure the realistic and consistent motion speed in your videos, especially to detect 'chronometric hallucinations' in AI-generated content.
Not ideal if you only need to know the technical metadata frame rate of a video or if you are not working with video content where motion realism is a concern.
Stars
12
Forks
1
Language
Python
License
—
Category
Last pushed
Mar 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/taco-group/Pulse-of-Motion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators