OpenMOSS unveils MOVA: Open-Source model for video and audio

Pubblicato il 2026-01-29 12:11 ℹ️ LocalLLaMA 📰 Leggi l'articolo originale →

OpenMOSS presenta MOVA: modello open-source per video e audio

OpenMOSS has announced the release of MOVA (MOSS-Video-and-Audio), a fully open-source artificial intelligence model designed for video and audio generation. The model stands out for its Mixture of Experts (MoE) architecture, with 18 billion active parameters out of a total of 32 billion.

Technical Details

MOVA offers day-0 support for SGLang-Diffusion, a framework that facilitates the creation of diffusion applications. The pre-trained MOVA-360p and MOVA-720p models are available on Hugging Face.

Resources

GitHub: https://github.com/OpenMOSS/MOVA
MOVA-360: https://huggingface.co/OpenMOSS-Team/MOVA-360p
MOVA-720p: https://huggingface.co/OpenMOSS-Team/MOVA-720p

Key Takeaway

OpenMOSS has released MOVA (MOSS-Video-and-Audio), a fully open-source model with 18 billion active parameters (MoE architecture, 32 billion total). MOVA offers day-0 support for SGLang-Diffusion and aims at scalable and synchronized video and audio generation.

🤖 Ask AI about this

Want to dive deeper? Read the full article from the source:

📖 READ THE ORIGINAL ARTICLE