FlashVSR: Towards Real-time Diffusion-Based Streaming Video Super-Resolution

ICLR 2026 Conference Submission18272 Authors

Keywords: Efficient Video Super-Resolution, Diffusion Models, Streaming Inference

TL;DR: FlashVSR is a one-step diffusion-based streaming framework that achieves real-time video super-resolution with high efficiency and scalability to ultra-high resolutions.

Abstract: Diffusion models have recently advanced video restoration, but applying them to real-world video super-resolution (VSR) remains challenging due to high latency, prohibitive computation, and poor generalization to ultra-high resolutions. Our goal in this work is to make diffusion-based VSR practical by achieving efficiency, scalability, and real-time performance. To this end, we propose **FlashVSR**, the first diffusion-based one-step streaming framework towards real-time VSR. FlashVSR runs at ~17 FPS for 768×1408 videos on a single A100 GPU by combining three complementary innovations: (i) a train-friendly three-stage distillation pipeline that enables streaming super-resolution, (ii) locality-constrained sparse attention that cuts redundant computation while bridging the train–test resolution gap, and (iii) a tiny conditional decoder that accelerates reconstruction without sacrificing quality. To support large-scale training, we also construct **VSR-120K**, a new dataset with 120k videos and 180k images. Extensive experiments show that FlashVSR scales reliably to ultra-high resolutions and achieves state-of-the-art performance with up to ~12× speedup over prior one-step diffusion VSR models. We will release code, models, and the dataset to foster future research in efficient diffusion-based VSR.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 18272