RCEpic
hkchengrex/MMAudio
[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
- Owner
- hkchengrex (personal account)
- Stars
- Stars: 2,303
- Forks
- Forks: 271
- Language
- Python
- License
- MIT
- Created
- 2024
- Topics
- audioaudio-synthesiscomputer-visiondeep-learningvideo-to-audiotext-to-audio
- Tier
- RC (2,000 to 4,999 ★) What this tier means
More repos by hkchengrex
All 8 repos by hkchengrex- hkchengrex/XMemStars: 1,997PythonBeta
- hkchengrex/Tracking-Anything-with-DEVAStars: 1,523PythonBeta
- hkchengrex/CutieStars: 1,125PythonBeta
- hkchengrex/CascadePSPStars: 888PythonBeta
- hkchengrex/STCNStars: 567PythonAlpha
- hkchengrex/MiVOSStars: 489PythonAlpha
Nearby in Python
All Python repos- LogosIntelligenceLab/Semantic-Segment-AnythingStars: 2,304PythonRC
- opendatalab/DocLayout-YOLOStars: 2,304PythonRC
- dstackai/dstackStars: 2,303PythonRC
- seb-m/pyinotifyStars: 2,302PythonRC
- mampfes/hacs_waste_collection_scheduleStars: 2,302PythonRC
- NVlabs/nvdiffrecStars: 2,301PythonRC