Hugging Face's logo

AEmotionStudio
/
Visual_Chronometer

Video Classification
video-understanding
fps-prediction
visual-chronometer
pulse-of-motion
Model card Files
xet
 Community
Visual_Chronometer / README.md
AEmotionStudio's picture
AEmotionStudio
Upload README.md with huggingface_hub
f4be79b verified
preview code
|
raw
history blame contribute delete
1.33 kB
metadata 
license: apache-2.0
tags:
  - video-understanding
  - fps-prediction
  - visual-chronometer
  - pulse-of-motion
pipeline_tag: video-classification

Visual Chronometer — Physical FPS Prediction

Safetensors conversion of the Visual Chronometer model for predicting the Physical Frame Rate (PhyFPS) from video motion patterns.

Model Details

  • Architecture: 2+1D VAE encoder + attention-pooled probe + MLP regression head
  • Training range: 10–60 FPS
  • Output: log(FPS) — take exp() to get predicted PhyFPS
  • Input: 30-frame clips at 216×216 resolution, normalized to [-1, 1]
  • Parameters: ~170M (683 MB safetensors)

Format

This repo provides the model in safetensors format, converted from the original PyTorch Lightning checkpoint.

File Size Format
vc_common_10_60fps.safetensors 683 MB safetensors

Original

Usage

Used by ComfyUI-FFMPEGA as the phyfps no-LLM mode for automated video temporal quality assessment.