OpenMOSS-Team / MOVA-720p

huggingface.co
Total runs: 343
24-hour runs: 0
7-day runs: -406
30-day runs: -751
Model's Last Updated: February 11 2026
any-to-any

Introduction of MOVA-720p

Model Details of MOVA-720p

MOVA: Towards Scalable and Synchronized Video–Audio Generation

We introduce MOVA ( MO SS V ideo and A udio), a foundation model designed to break the "silent era" of open-source video generation. Unlike cascaded pipelines that generate sound as an afterthought, MOVA synthesizes video and audio simultaneously for perfect alignment.

🌟Key Highlights

  • Native Bimodal Generation : Moves beyond clunky cascaded pipelines. MOVA generates high-fidelity video and synchronized audio in a single inference pass, eliminating error accumulation.
  • Precise Lip-Sync & Sound FX : Achieves state-of-the-art performance in multilingual lip-synchronization and environment-aware sound effects.
  • Fully Open-Source : In a field dominated by closed-source models (Sora 2, Veo 3, Kling), we are releasing model weights, inference code, training pipelines, and LoRA fine-tuning scripts.
  • Asymmetric Dual-Tower Architecture : Leverages the power of pre-trained video and audio towers, fused via a bidirectional cross-attention mechanism for rich modality interaction.
Demo
Model Details
Model Description

MOVA addresses the limitations of proprietary systems like Sora 2 and Veo 3 by offering a fully open-source framework for Image-to-Video-Audio (IT2VA) and Text-to-Video-Audio (T2VA) tasks. The model employs an asymmetric dual-tower architecture fused via a bidirectional cross-attention mechanism, leveraging a Mixture-of-Experts (MoE) design with 32B total parameters (18B active during inference) to ensure high-quality synthesis with efficient deployment. Alongside the model weights, we provide a fine-grained bimodal data pipeline and support for LoRA fine-tuning, empowering the community to advance research in synchronized cinematic synthesis.

Model Sources
Model Usage

Please refer to the github page for model usage.

Evaluation

We evaluate our model through both objective benchmarks and subjective human evaluations. Below are the Elo scores and win rates comparing MOVA to existing open-source models.

Runs of OpenMOSS-Team MOVA-720p on huggingface.co

343
Total runs
0
24-hour runs
-132
3-day runs
-406
7-day runs
-751
30-day runs

More Information About MOVA-720p huggingface.co Model

More MOVA-720p license Visit here:

https://choosealicense.com/licenses/apache-2.0

MOVA-720p huggingface.co

MOVA-720p huggingface.co is an AI model on huggingface.co that provides MOVA-720p's model effect (), which can be used instantly with this OpenMOSS-Team MOVA-720p model. huggingface.co supports a free trial of the MOVA-720p model, and also provides paid use of the MOVA-720p. Support call MOVA-720p model through api, including Node.js, Python, http.

OpenMOSS-Team MOVA-720p online free

MOVA-720p huggingface.co is an online trial and call api platform, which integrates MOVA-720p's modeling effects, including api services, and provides a free online trial of MOVA-720p, you can try MOVA-720p online for free by clicking the link below.

OpenMOSS-Team MOVA-720p online free url in huggingface.co:

https://huggingface.co/OpenMOSS-Team/MOVA-720p

MOVA-720p install

MOVA-720p is an open source model from GitHub that offers a free installation service, and any user can find MOVA-720p on GitHub to install. At the same time, huggingface.co provides the effect of MOVA-720p install, users can directly use MOVA-720p installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

MOVA-720p install url in huggingface.co:

https://huggingface.co/OpenMOSS-Team/MOVA-720p

Url of MOVA-720p

Provider of MOVA-720p huggingface.co

OpenMOSS-Team
ORGANIZATIONS

Other API from OpenMOSS-Team

huggingface.co

Total runs: 109
Run Growth: -111
Growth Rate: -101.83%
Updated:September 26 2023