--- title: MOVA-360p canonical_url: "https://www.modelscope.cn/models/OpenMOSS/MOVA-360p" md_url: "https://www.modelscope.cn/models/OpenMOSS/MOVA-360p.md" repository: OpenMOSS/MOVA-360p last_updated: 2026-02-15 license: apache-2.0 parameters: 38.8B tensor_type: - BF16 library_name: - safetensors - diffusers - pytorch frameworks: - pytorch downloads: 2702 stars: 2 tags: - image-to-video - image-text-to-video - image-to-audio-video - image-text-to-audio-video - MOVA - OpenMOSS - SII - MOSI - sglang-diffusion --- # MOVA-360p > MOVA-360p - OpenMOSS 在 ModelScope 开源的模型。MOVA: Towards Scalable and Synchronized Video–Audio Generation We introduce MOVA (MOSS Video and Audio), a foundation model designed to break the "silent era" of open-source video generation. Unlike cascaded pipelines… OpenMOSS/MOVA-360p 是 ModelScope 魔搭社区上的 38.8B 参数机器学习模型，采用 apache-2.0 许可。 - **Repository**: OpenMOSS/MOVA-360p - **License**: apache-2.0 - **Parameters**: 38.8B - **Tags**: image-to-video, image-text-to-video, image-to-audio-video, image-text-to-audio-video, MOVA, OpenMOSS, SII, MOSI, sglang-diffusion - **Downloads**: 2702 - **Stars**: 2 - **Last updated**: 2026-02-15 Source: https://www.modelscope.cn/models/OpenMOSS/MOVA-360p --- ## 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 - **Github:** https://github.com/OpenMOSS/MOVA - **Paper:** https://arxiv.org/pdf/2602.08794 ### 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.