AutoMV: An Automatic Multi-Agent System for Music Video Generation
cs.MM, cs.CV, cs.SD, eess.AS
Submitted: 2025-12-13
Updated: 2026-11-17
Code: https://github.com/multimodal-art-projection/AutoMV
Project page: https://m-a-p.ai/AutoMV/Abstract
Terminology
Sources
- PIXART-{\delta}: Fast and Controllable Image Generation with Latent Consistency Models
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Seedance 1.0: Exploring the Boundaries of Video Generation Models
- ImageBind: One Embedding Space To Bind Them All
- Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
- SongFormer: Scaling Music Structure Analysis with Heterogeneous Supervision
- GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
- OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
- OmniBench: Towards The Future of Universal Omni-Language Models
- Open-Sora Plan: Open-Source Large Video Generation Model
- VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
- Foundation Models for Music: A Survey
- MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
- Cross-Modal Learning for Music-to-Music-Video Description Generation
- OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
- Wan: Open and Advanced Large-Scale Video Generative Models
- Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration
- Qwen2.5-Omni Technical Report
- YuE: Scaling Open Foundation Models for Long-Form Music Generation
- Long-Video Audio Synthesis with Multi-Agent Collaboration
Related papers
- FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
- When does the head leave? Shared timing and a movement clock in 360-degree video viewing
- Augmented Hybrid TV Services. Habits, Preferences, Opinions and Expectations of Spanish Consumers
- A Survey of Generative Categories and Techniques in Multimodal Generative Models
- ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling
- EyeNavGS: A 6-DoF Navigation Dataset and Record-n-Replay Software for Real-World 3DGS Scenes in VR