# Waver: Wave Your Way to Lifelike Video Generation

arXiv: https://arxiv.org/abs/2508.15761 · HTML: https://mlsanity.com/paper/2508.15761/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 43 references that are in the map.
- First posted on arXiv 21 Aug 2025.

## Builds on (most cited first, 30 of 37)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [Seedance 1.0: Exploring the Boundaries of Video Generation Models](https://mlsanity.com/paper/2506.09113/) (2025)
- [Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning](https://mlsanity.com/paper/2311.10709/) (2023)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive](https://mlsanity.com/paper/2402.13228/) (2024)
- [Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity](https://mlsanity.com/paper/2502.01776/) (2025)
- [Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model](https://mlsanity.com/paper/2502.10248/) (2025)
- [Fast Video Generation with Sliding Tile Attention](https://mlsanity.com/paper/2502.04507/) (2025)
- [Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models](https://mlsanity.com/paper/2410.02416/) (2024)
- [Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model](https://mlsanity.com/paper/2504.08685/) (2025)

## Built on by (most cited first, 30 of 52)

- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [Advancing Open-source World Models](https://mlsanity.com/paper/2601.20540/) (2026)
- [SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://mlsanity.com/paper/2509.24695/) (2025)
- [InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation](https://mlsanity.com/paper/2511.04675/) (2025)
- [Pack and Force Your Memory: Long-form and Consistent Video Generation](https://mlsanity.com/paper/2510.01784/) (2025)
- [Region-Constraint In-Context Generation for Instructional Video Editing](https://mlsanity.com/paper/2512.17650/) (2025)
- [PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation](https://mlsanity.com/paper/2512.24551/) (2025)
- [MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation](https://mlsanity.com/paper/2510.18692/) (2025)
- [LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts](https://mlsanity.com/paper/2602.11564/) (2026)
- [Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence](https://mlsanity.com/paper/2607.07675/) (2026)
- [Bernini: Latent Semantic Planning for Video Diffusion](https://mlsanity.com/paper/2605.22344/) (2026)
- [Scaling Zero-Shot Reference-to-Video Generation](https://mlsanity.com/paper/2512.06905/) (2025)
- [DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer](https://mlsanity.com/paper/2601.01425/) (2026)
- [ALIVE: Animate Your World with Lifelike Audio-Video Generation](https://mlsanity.com/paper/2602.08682/) (2026)
- [Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation](https://mlsanity.com/paper/2604.10103/) (2026)
- [OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation](https://mlsanity.com/paper/2604.11804/) (2026)
- [ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generation](https://mlsanity.com/paper/2511.00511/) (2025)
- [A Mechanistic View on Video Generation as World Models: State and Dynamics](https://mlsanity.com/paper/2601.17067/) (2026)
- [AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising](https://mlsanity.com/paper/2603.14331/) (2026)
- [Echo-Memory: A Controlled Study of Memory in Action World Models](https://mlsanity.com/paper/2606.09803/) (2026)
- [DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning](https://mlsanity.com/paper/2601.21716/) (2026)
- [FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space](https://mlsanity.com/paper/2602.02092/) (2026)
- [Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms](https://mlsanity.com/paper/2603.28489/) (2026)
- [TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction](https://mlsanity.com/paper/2511.12578/) (2025)
- [AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization](https://mlsanity.com/paper/2603.17461/) (2026)
- [Improving Joint Audio-Video Generation with Cross-Modal Context Learning](https://mlsanity.com/paper/2603.18600/) (2026)
- [AdaPower: Specializing World Foundation Models for Predictive Manipulation](https://mlsanity.com/paper/2512.03538/) (2025)
- [Transform Trained Transformer for Accelerating Native 4K Video Generation](https://mlsanity.com/paper/2512.13492/) (2025)

## Abstract (arXiv)

We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2V), and text-to-image (T2I) generation within a single, integrated framework. We introduce a Hybrid Stream DiT architecture to enhance modality alignment and accelerate training convergence. To ensure training data quality, we establish a comprehensive data curation pipeline and manually annotate and train an MLLM-based video quality model to filter for the highest-quality samples. Furthermore, we provide detailed training and inference recipes to facilitate the generation of high-quality videos. Building on these contributions, Waver excels at capturing complex motion, achieving superior motion amplitude and temporal consistency in video synthesis. Notably, it ranks among the Top 3 on both the T2V and I2V leaderboards at Artificial Analysis (data as of 2025-07-30 10:00 GMT+8), consistently outperforming existing open-source models and matching or surpassing state-of-the-art commercial solutions. We hope this technical report will help the community more efficiently train high-quality video generation models and accelerate progress in video generation technologies. Official page: https://github.com/FoundationVision/Waver.