# Wan-S2V: Audio-Driven Cinematic Video Generation

arXiv: https://arxiv.org/abs/2508.18621 · HTML: https://mlsanity.com/paper/2508.18621/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Builds on (most cited first, 16 of 16)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions](https://mlsanity.com/paper/2402.17485/) (2024)
- [MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance](https://mlsanity.com/paper/2406.19680/) (2024)
- [Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models](https://mlsanity.com/paper/2504.12626/) (2025)
- [Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content](https://mlsanity.com/paper/2410.08260/) (2024)
- [OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models](https://mlsanity.com/paper/2502.01061/) (2025)
- [FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis](https://mlsanity.com/paper/2504.04842/) (2025)
- [HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters](https://mlsanity.com/paper/2505.20156/) (2025)
- [A Light Weight Model for Active Speaker Detection](https://mlsanity.com/paper/2303.04439/) (2023)
- [EMO2: End-Effector Guided Audio-Driven Avatar Video Generation](https://mlsanity.com/paper/2501.10687/) (2025)

## Built on by (most cited first, 30 of 61)

- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [UniVerse-1: Unified Audio-Video Generation via Stitching of Experts](https://mlsanity.com/paper/2509.06155/) (2025)
- [UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions](https://mlsanity.com/paper/2511.03334/) (2025)
- [JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation](https://mlsanity.com/paper/2602.19163/) (2026)
- [Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis](https://mlsanity.com/paper/2509.09595/) (2025)
- [AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement](https://mlsanity.com/paper/2511.23475/) (2025)
- [KlingAvatar 2.0 Technical Report](https://mlsanity.com/paper/2512.13313/) (2025)
- [Mode Seeking meets Mean Seeking for Fast Long Video Generation](https://mlsanity.com/paper/2602.24289/) (2026)
- [LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation](https://mlsanity.com/paper/2510.08318/) (2025)
- [Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation](https://mlsanity.com/paper/2512.21734/) (2025)
- [LPM 1.0: Video-based Character Performance Model](https://mlsanity.com/paper/2604.07823/) (2026)
- [SoulX-FlashTalk: Real-Time Infinite Streaming of Audio-Driven Avatars via Self-Correcting Bidirectional Distillation](https://mlsanity.com/paper/2512.23379/) (2025)
- [ASTRA: Let Arbitrary Subjects Transform in Video Editing](https://mlsanity.com/paper/2510.01186/) (2025)
- [AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising](https://mlsanity.com/paper/2603.14331/) (2026)
- [LongCat-Video-Avatar 1.5 Technical Report](https://mlsanity.com/paper/2605.26486/) (2026)
- [3MDiT: Unified Tri-Modal Diffusion Transformer for Text-Driven Synchronized Audio-Video Generation](https://mlsanity.com/paper/2511.21780/) (2025)
- [ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars](https://mlsanity.com/paper/2512.19546/) (2025)
- [EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields](https://mlsanity.com/paper/2605.06192/) (2026)
- [Understanding, Accelerating, and Improving MeanFlow Training](https://mlsanity.com/paper/2511.19065/) (2025)
- [MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation](https://mlsanity.com/paper/2512.03034/) (2025)
- [SoulX-FlashHead: Oracle-guided Generation of Infinite Real-time Streaming Talking Heads](https://mlsanity.com/paper/2602.07449/) (2026)
- [Improving Joint Audio-Video Generation with Cross-Modal Context Learning](https://mlsanity.com/paper/2603.18600/) (2026)
- [Vidu S1: A Real-Time Interactive Video Generation Model](https://mlsanity.com/paper/2607.03118/) (2026)
- [JoyStreamer-Flash: Real-time and Infinite Audio-Driven Avatar Generation with Autoregressive Diffusion](https://mlsanity.com/paper/2512.11423/) (2025)
- [Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation](https://mlsanity.com/paper/2512.13495/) (2025)
- [TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation](https://mlsanity.com/paper/2512.14938/) (2025)
- [Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars](https://mlsanity.com/paper/2602.01538/) (2026)
- [CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation](https://mlsanity.com/paper/2604.19636/) (2026)
- [StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration](https://mlsanity.com/paper/2605.25659/) (2026)
- [OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data](https://mlsanity.com/paper/2606.30019/) (2026)

## Abstract (arXiv)

Current state-of-the-art (SOTA) methods for audio-driven character animation demonstrate promising performance for scenarios primarily involving speech and singing. However, they often fall short in more complex film and television productions, which demand sophisticated elements such as nuanced character interactions, realistic body movements, and dynamic camera work. To address this long-standing challenge of achieving film-level character animation, we propose an audio-driven model, which we refere to as Wan-S2V, built upon Wan. Our model achieves significantly enhanced expressiveness and fidelity in cinematic contexts compared to existing approaches. We conducted extensive experiments, benchmarking our method against cutting-edge models such as Hunyuan-Avatar and Omnihuman. The experimental results consistently demonstrate that our approach significantly outperforms these existing solutions. Additionally, we explore the versatility of our method through its applications in long-form video generation and precise video lip-sync editing.