VidMuse

HKUSTAudio/VidMuse

audiocraftLicense: cc-by-4.0
Tracked by OpenModelStats since November 16, 2026View on Hugging Face ↗
Downloads 30D
2,257
Total downloads
5,005
Gained 7D
—
Gained 30D
—
Likes
7
Rank · tracked models
#21,716
–this week
Parameters
—
Last source update
May 8, 2025

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-11-16. Charts appear as daily observations accumulate.

Overview

VidMuse is an AI model published by HKUSTAudio. OpenModelStats has tracked the model since Nov 16, 2026, most recently observing it Nov 18, 2026.

Published
Mar 1, 2025
Last updated
May 8, 2025
Library
audiocraft
License
cc-by-4.0
Task
—
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
—
audiocraftpytorchvideo-to-audioarxiv:2406.04321license:cc-by-4.0region:us

Similar models

Models similar to VidMuse
ModelDL 30D
all-MiniLM-L6-v2sentence-transformers167.7M
whisperkit-coremlargmaxinc84.3M
ms-marco-MiniLM-L6-v2cross-encoder56.3M
bge-small-en-v1.5BAAI43.6M
gpt2openai-community34.3M
chronos-2autogluon34.2M