StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation
Tianrui Feng, Zhi Li, Shuo Yang, Haocheng Xi, Muyang Li, Xiuyu Li, Lvmin Zhang, Keting Yang, Kelly Peng, Song Han, Maneesh Agrawala, Kurt Keutzer, Akio Kodaira, Chenfeng Xu

TL;DR
StreamDiffusionV2 is a real-time, scalable video diffusion system designed for live streaming, achieving low latency and high FPS across heterogeneous GPUs through system-level optimizations and parallelization.
Contribution
It introduces a training-free, SLO-aware streaming pipeline with novel scheduling and caching techniques, enabling practical, high-quality live video generation at scale.
Findings
First frame rendered within 0.5 seconds
Achieves 58.28 FPS with 14B model on four H100 GPUs
Supports flexible denoising steps for low latency or high quality
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage and Video Quality Assessment · Video Coding and Compression Technologies · Peer-to-Peer Network Technologies
