Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions

• URL: http://arxiv.org/abs/2606.09150v2
• Date: Mon, 15 Jun 2026 06:34:05 GMT
• Title: Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
• Abstract summary: Ultra Flash is a cascaded streaming framework capable of real-time high-resolution video generation.<n>It produces ultra-high-resolution streaming video while maintaining state-of-the-art visual quality and superior efficiency.
• Score: 69.01904860240938
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While recent autoregressive video diffusion models achieve remarkable streaming quality, they remain confined to low resolutions (e.g., 480P), leaving efficient, scalable, real-time high-resolution video generation a fundamental open challenge. To bridge this gap, we present Ultra Flash, a cascaded streaming framework capable of real-time high-resolution video generation. Ultra Flash achieves ~30 FPS at 1K resolution and ~18 FPS at 2K resolution on a single GPU through three key contributions: (1) an architecture-preserving T2V-to-TV2V super-resolution training paradigm coupled with an AIGC-oriented data degradation pipeline that effectively preserves the generative capability of the base model, enabling enhanced high-resolution detail when cascaded after mainstream low-resolution generative models; (2) a causal streaming latent upsampler paired with a high-resolution decoder, which enhances spatiotemporal coherence while enabling efficient latent spatial scaling and precise high-resolution decoding with negligible computational overhead; and (3) a cascade high-resolution streaming video generation optimization scheme that first performs hybrid-reward-enhanced sparse causalization and single-step distillation of the super-resolution model, then introduces cascaded streaming self-forcing preference optimization with dynamic cache management, jointly enhancing overall coherence, improving quality, and enabling real-time high-resolution streaming video generation. Extensive experiments demonstrate that Ultra Flash reliably produces ultra-high-resolution streaming video while maintaining state-of-the-art visual quality and superior efficiency. Project Page: https://xin1u.github.io/UltraFlash/

Related papers

• ViBe: Ultra-High-Resolution Video Synthesis Born from Pure Images [30.646542711556787]
  Transformer-based video diffusion models rely on 3D attention over spatial and temporal tokens.<n>We propose a pure image adaptation framework that upgrades a video Diffusion Transformer pre-trained at its native scale to synthesize higher-resolution videos.
  arXiv  Detail & Related papers  (2026-03-24T15:27:22Z)
• Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model [47.71265147565265]
  Vision foundation model (VFM) is used to harness the powerful video understanding and processing capacities.<n>We present the first revolutionized paradigm that enables VFM-based end-to-end generative streaming.<n>Morphe achieves comparable visual quality while saving 62.5% bandwidth compared to H.265, and real-time, loss-resilient video delivery in challenging network environments.
  arXiv  Detail & Related papers  (2026-02-03T13:47:18Z)
• HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming [58.55148690302855]
  HiStream is an efficient autoregressive framework that systematically reduces redundancy across three axes.<n>On 1080p benchmarks, our primary HiStream model (i+ii) achieves state-of-the-art visual quality while demonstrating up to 76.2x faster denoising compared to the Wan2.1 baseline.<n>Our faster variant, HiStream+, applies all three optimizations, achieving a 107.5x acceleration over the baseline.
  arXiv  Detail & Related papers  (2025-12-24T18:59:58Z)
• StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation [65.90400162290057]
  Generative models are reshaping the live-streaming industry by redefining how content is created, styled, and delivered.<n>Recent advances in video diffusion have markedly improved temporal consistency and sampling efficiency for offline generation.<n>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.
  arXiv  Detail & Related papers  (2025-11-10T18:51:28Z)
• UltraGen: High-Resolution Video Generation with Hierarchical Attention [62.99161115650818]
  UltraGen is a novel video generation framework that enables i) efficient and ii) end-to-end native high-resolution video synthesis.<n>We show that UltraGen can effectively scale pre-trained low-resolution video models to 1080P and even 4K resolution for the first time.
  arXiv  Detail & Related papers  (2025-10-21T16:23:21Z)
• VividFace: High-Quality and Efficient One-Step Diffusion For Video Face Enhancement [51.83206132052461]
  Video Face Enhancement (VFE) seeks to reconstruct high-quality facial regions from degraded video sequences.<n>Current methods that rely on video super-resolution and generative frameworks face three fundamental challenges.<n>We propose VividFace, a novel and efficient one-step diffusion framework for video face enhancement.
  arXiv  Detail & Related papers  (2025-09-28T02:39:48Z)
• FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation [61.61415607972597]
  DiT diffusion models have achieved great success in text-to-video generation, leveraging their scalability in model capacity and data scale.<n>High content and motion fidelity aligned with text prompts, however, often require large model parameters and a substantial number of function evaluations (NFEs)<n>We propose a novel two stage framework, FlashVideo, which strategically allocates model capacity and NFEs across stages to balance generation fidelity and quality.
  arXiv  Detail & Related papers  (2025-02-07T18:59:59Z)
• CascadeV: An Implementation of Wurstchen Architecture for Video Generation [4.086317089863318]
  We propose a cascaded latent diffusion model (LDM) that is capable of producing state-of-the-art 2K resolution videos.<n> Experiments demonstrate that our cascaded model achieves a higher compression ratio, substantially reducing the computational challenges associated with high-quality video generation.<n>Our model can be cascaded with existing T2V models, theoretically enabling a 4$times$ increase in resolution or frames per second without any fine-tuning.
  arXiv  Detail & Related papers  (2025-01-28T01:14:24Z)
• DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradations [25.756755602342942]
  We present DiffVSR, featuring a Progressive Learning Strategy (PLS) that systematically decomposes this learning burden through staged training.<n>Our framework additionally incorporates an Interweaved Latent Transition (ILT) technique that maintains competitive temporal consistency without additional training overhead.
  arXiv  Detail & Related papers  (2025-01-17T10:53:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.