# StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation

arXiv: https://arxiv.org/abs/2511.07399 · HTML: https://mlsanity.com/paper/2511.07399/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 45 of its 49 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion](https://mlsanity.com/paper/2310.02279/) (2023)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models](https://mlsanity.com/paper/2410.11081/) (2024)
- [MAGI-1: Autoregressive Video Generation at Scale](https://mlsanity.com/paper/2505.13211/) (2025)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models](https://mlsanity.com/paper/2410.10733/) (2024)
- [Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity](https://mlsanity.com/paper/2502.01776/) (2025)
- [Matrix-game 2.0: An open-source real-time and streaming interactive world model](https://mlsanity.com/paper/2508.13009/) (2025)
- [Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers](https://mlsanity.com/paper/2406.01125/) (2024)
- [SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration](https://mlsanity.com/paper/2410.02367/) (2024)
- [Cache Me if You Can: Accelerating Diffusion Models through Block Caching](https://mlsanity.com/paper/2312.03209/) (2023)
- [FORA: Fast-Forward Caching in Diffusion Transformer Acceleration](https://mlsanity.com/paper/2407.01425/) (2024)

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

- [Helios: Real Real-Time Long Video Generation Model](https://mlsanity.com/paper/2603.04379/) (2026)
- [Infinite Worlds with Versatile Interactions](https://mlsanity.com/paper/2607.07534/) (2026)
- [Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization](https://mlsanity.com/paper/2602.02958/) (2026)
- [TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model](https://mlsanity.com/paper/2601.00051/) (2025)
- [LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing](https://mlsanity.com/paper/2606.26740/) (2026)
- [Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond](https://mlsanity.com/paper/2604.22748/) (2026)
- [Alaya-EVOKE: From Linear-Scaling Supervision to Endless World](https://mlsanity.com/paper/2608.13546/) (2026)
- [SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing](https://mlsanity.com/paper/2603.08982/) (2026)
- [BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation](https://mlsanity.com/paper/2511.22973/) (2025)
- [EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing](https://mlsanity.com/paper/2512.06065/) (2025)
- [JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion](https://mlsanity.com/paper/2608.03974/) (2026)
- [Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation](https://mlsanity.com/paper/2609.11638/) (2026)
- [Adapting VACE for Real-Time Autoregressive Video Diffusion](https://mlsanity.com/paper/2602.14381/) (2026)
- [Vidu S1: A Real-Time Interactive Video Generation Model](https://mlsanity.com/paper/2607.03118/) (2026)
- [Instruction-Based Video Editing by Repurposing an Image Editing Model](https://mlsanity.com/paper/2608.14790/) (2026)
- [StreamFlow: Theory, Algorithm, and Implementation for High-Efficiency Rectified Flow Generation](https://mlsanity.com/paper/2511.22009/) (2025)
- [Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery](https://mlsanity.com/paper/2603.05811/) (2026)
- [Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation](https://mlsanity.com/paper/2609.20744/) (2026)
- [StreamWise: Serving Multi-Modal Generation in Real-Time at Scale](https://mlsanity.com/paper/2603.05800/) (2026)
- [Q-ARVD: Quantizing Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2605.21072/) (2026)
- [Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU](https://mlsanity.com/paper/2606.05981/) (2026)
- [Stateful Worlds, Stateless Elasticity: Exact-State Serving for Interactive World Models](https://mlsanity.com/paper/2607.10389/) (2026)
- [InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter](https://mlsanity.com/paper/2608.20910/) (2026)
- [EditaLive! Unified Character Video Editing for Live Streaming](https://mlsanity.com/paper/2608.27123/) (2026)
- [Rethinking Streaming Video Diffusion Model: Context, Execution, and Training](https://mlsanity.com/paper/2609.22283/) (2026)
- [Streaming Video Editing with Easy Adaptation](https://mlsanity.com/paper/2609.24788/) (2026)
- [WorldAttention: An Efficient Attention Architecture for Interactive Video World Models](https://mlsanity.com/paper/2609.34606/) (2026)
- [Weave Forcing: Compositional Memory Routing for Interactive Long Video Generation](https://mlsanity.com/paper/2610.03510/) (2026)
- [A Spatiotemporal Semantic Importance-Guided Unified Compression and Editing Framework for AI-Generated Videos](https://mlsanity.com/paper/2610.05779/) (2026)
- [VIS-Ground: Video Interactive Storytelling with Contextual Grounding](https://mlsanity.com/paper/2610.09326/) (2026)

## Abstract (arXiv)

Generative models are reshaping the live-streaming industry by redefining how content is created, styled, and delivered. Previous image-based streaming diffusion models have powered efficient and creative live streaming products but have hit limits on temporal consistency due to the foundation of image-based designs. Recent advances in video diffusion have markedly improved temporal consistency and sampling efficiency for offline generation. However, offline generation systems primarily optimize throughput by batching large workloads. In contrast, live online streaming operates under strict service-level objectives (SLOs): time-to-first-frame must be minimal, and every frame must meet a per-frame deadline with low jitter. Besides, scalable multi-GPU serving for real-time streams remains largely unresolved so far. To address this, we present StreamDiffusionV2, a training-free pipeline for interactive live streaming with video diffusion models. StreamDiffusionV2 integrates an SLO-aware batching scheduler and a block scheduler, together with a sink-token--guided rolling KV cache, a motion-aware noise controller, and other system-level optimizations. Moreover, we introduce a scalable pipeline orchestration that parallelizes the diffusion process across denoising steps and network layers, achieving near-linear FPS scaling without violating latency guarantees. The system scales seamlessly across heterogeneous GPU environments and supports flexible denoising steps (e.g., 1--4), enabling both ultra-low-latency and higher-quality modes. Without TensorRT or quantization, StreamDiffusionV2 renders the first frame within 0.5s and attains 58.28 FPS with a 14B-parameter model and 64.52 FPS with a 1.3B-parameter model on four H100 GPUs, making state-of-the-art generative live streaming practical and accessible--from individual creators to enterprise-scale platforms.