Spaces:
Running on Zero
Download README.md from hugging-apps/vae-rhythm: direct link, hf CLI and curl.
- Browser
- Download file 3.13 kB
-
https://huggingface.co/spaces/hugging-apps/vae-rhythm/resolve/main/README.md
- Command line
-
hf download hf://spaces/hugging-apps/vae-rhythm/README.md
-
curl -L -o README.md https://huggingface.co/spaces/hugging-apps/vae-rhythm/resolve/main/README.md
title: VAE Rhythm
emoji: πΌ
colorFrom: yellow
colorTo: indigo
sdk: gradio
sdk_version: 6.32.0
app_file: app.py
python_version: '3.12'
startup_duration_timeout: 1h
short_description: Detect AI-generated video via VAE decoding traces
VAE Rhythm: Temporal Decoding Traces for AI-Generated Video Detection
Demo for the paper VAE Rhythm: Temporal Decoding Traces for AI-Generated Video Detection (arXiv 2611.21114, Show Lab Β· NUS). It ships the paper's two detectors:
- Phase scan (training-free) β re-encode a clip with the paper's protocol (x264 CRF 23, GOP 32, short side capped at 720 px), reconstruct K=24 successive W=13-frame windows with a frozen causal Wan2.1 video VAE, and read the periodicity of the reconstruction-error residual. Generated videos are decoded in frame groups, so their error profile repeats with the group period; real videos give a nearly flat one.
- CaDet (trained detector, Jack97/CaDet) β two parameter-efficient paths on a frozen DINOv3 ViT-L/16 read 8 frames per clip and output a sum of z-scores standardised on real validation videos.
Interpretation
- Phase scan: a high z(Ppk) (above β 2.35, the 95th percentile of real videos) is evidence that a clip was decoded by a causal video VAE. A low value is not evidence that a video is real β low motion, frame-rate conversion, upscaling and re-encoding all weaken the rhythm.
- CaDet: the score is a z-score sum (β 0 for typical real videos, larger = more likely generated), not a probability. Operating points shift across real-video sources; heavily re-encoded, very short or low-resolution clips are harder.
- Neither score alone is a definitive real/fake verdict.
Examples
Each example is a VAE pair built with the paper's own recipe: a stock clip from the CC0 dataset linoyts/repo-to-space-example-videos, protocol-encoded, next to a copy of the same frames through one Wan2.1 VAE round trip re-encoded with the same chain. The pairs showcase the contrast a VAE round trip leaves in the traces. Measured on this Space: the cat pair scans Ppk 0.477 vs 0.091 (C8 0.82 vs 0.11) and the rope pair 0.311 vs 0.135 (low motion β see the warning in the app), while the 50 fps veggie pair's scan contrast is weak (frame-rate conversion weakens the rhythm, as the interpretation rules note). The CaDet score rises for the round-trip twin in all three pairs (β0.84ββ0.20, 2.62β3.10, 3.30β5.69). Clip names are neutral on purpose β no ground-truth authenticity claim is made about the stock footage itself.
References
- Paper: Sun, Li, Mei, Shou. VAE Rhythm: Temporal Decoding Traces for AI-Generated Video Detection. arXiv 2611.21114 (2026).
- Code: showlab/vae-rhythm (MIT).
- Detector weights: Jack97/CaDet.
- Project page: showlab.github.io/vae-rhythm.