PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution

• URL: http://arxiv.org/abs/2605.25801v1
• Date: Mon, 25 May 2026 12:50:49 GMT
• Title: PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution
• Abstract summary: PixelWizard achieves superior visual quality while accelerating the generative sampling of native 2K/4K videos by over 10x.<n> experiments demonstrate that PixelWizard achieves superior visual quality while accelerating the generative sampling of native 2K/4K videos by over 10x.
• Score: 29.787554159107486
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-resolution video generation faces a coupled bottleneck of optimization instability and prohibitive computational costs. The massive expansion of the token sequence not only biases optimization toward local textures at the expense of global coherence, leading to structural collapse, but also imposes prohibitive training costs and severe inference latency. To address this, we propose PixelWizard, a framework that hierarchically decouples global structure modeling from fine-grained detail synthesis. PixelWizard first establishes a compact spatiotemporal anchor to concentrate dense structural priors, which then guides fine-grained generation at high resolution. This mitigates the local optimization bias to ensure structural stability without compromising high-frequency details. Leveraging this structural stability, we introduce Noise-Span Aligned Shortcut Training to break the inference bottleneck. By explicitly modeling the step size, this mechanism allows the model to traverse the generation trajectory with large steps. Crucially, we incorporate Exponential Index-Biased Sampling and Adaptive Noise-Span Calibration to align optimization with the shifted noise schedules of high-resolution grids, ensuring robust few-step inference without incurring the heavy overhead of distillation. Extensive experiments demonstrate that PixelWizard achieves superior visual quality while accelerating the generative sampling of native 2K/4K videos by over 10x.

Related papers

• Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions [69.01904860240938]
  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.
  arXiv  Detail & Related papers  (2026-06-08T07:45:03Z)
• RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling [51.279397568734424]
  Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis.<n>DiTs suffer from high inference latency and computational costs due to the quadratic complexity of 3D attention.<n>We introduce bftextRhymeFlow, a training-free framework that decouples the denoising trajectories of different frames.
  arXiv  Detail & Related papers  (2026-06-04T15:49:37Z)
• Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization [5.814544128372275]
  Oracle Noise is a zero-shot framework reframing noise as semantic-driven optimization strictly confined to a hypersphere.<n>It significantly accelerates semantic alignment and superior aesthetics without black-box models.<n>It achieves state-of-the-art performance across human preference metrics (e.g., HPSv2, ImageReward), semantic alignment (CLIP Score), and sample diversity, all within a strict 2-second optimization budget.
  arXiv  Detail & Related papers  (2026-04-26T05:32:26Z)
• Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation [9.132288507881592]
  Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention.<n>We propose Precision-Allocated Sparse Attention (PASA), a training-free framework designed for highly efficient and temporally smooth video generation.
  arXiv  Detail & Related papers  (2026-04-14T02:51:52Z)
• ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors [48.033666517340464]
  ScrollScape is a novel framework that reformulates EAR image synthesis into a continuous video generation process.<n>We show that ScrollScape significantly outperforms existing image-diffusion baselines by eliminating severe localized artifacts.
  arXiv  Detail & Related papers  (2026-03-25T13:03:02Z)
• SCEESR: Semantic-Control Edge Enhancement for Diffusion-Based Super-Resolution [0.8122270502556375]
  Real-world image super-resolution must handle complex degradations and inherent reconstruction ambiguities.<n>One-step diffusion models offer speed but often produce structural inaccuracies due to distillation artifacts.<n>We propose a novel SR framework that enhances a one-step diffusion model using a ControlNet mechanism for semantic edge guidance.
  arXiv  Detail & Related papers  (2025-10-22T06:06:01Z)
• Scale-DiT: Ultra-High-Resolution Image Generation with Hierarchical Local Attention [50.391914489898774]
  Scale-DiT is a new diffusion framework that introduces hierarchical local attention with low-resolution global guidance.<n>A lightweight LoRA adaptation bridges global and local pathways during denoising, ensuring consistency across structure and detail.<n>Experiments demonstrate that Scale-DiT achieves more than $2times$ faster inference and lower memory usage.
  arXiv  Detail & Related papers  (2025-10-18T03:15:26Z)
• Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events [71.2439653098351]
  Continuous space-time video super-STVSR has garnered increasing interest for its capability to reconstruct high-resolution and high-frame-rate videos at arbitrary temporal scales.<n>We present EvEnhancer, a novel approach that marries unique properties of high temporal and high dynamic range encapsulated in event streams.<n>Our method achieves state-of-the-art performance on both synthetic and real-world datasets, while maintaining generalizability at OOD scales.
  arXiv  Detail & Related papers  (2025-10-04T15:23:07Z)
• Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention [54.15345846343084]
  We propose Ultra3D, an efficient 3D generation framework that significantly accelerates sparse voxel modeling without compromising quality.<n>Part Attention is a geometry-aware localized attention mechanism that restricts attention computation within semantically consistent part regions.<n>Experiments demonstrate that Ultra3D supports high-resolution 3D generation at 1024 resolution and achieves state-of-the-art performance in both visual fidelity and user preference.
  arXiv  Detail & Related papers  (2025-07-23T17:57:16Z)
• Optimal Stepsize for Diffusion Sampling [14.849487881523041]
  Diffusion models achieve remarkable generation quality but suffer from computational intensive sampling due to suboptimal step discretization.<n>This paper proposes Optimal Stepsize Distillation, a dynamic programming framework that extracts theoretically optimal schedules by distilling knowledge from reference trajectories.<n> Experiments show 10x accelerated text-to-image generation while preserving 99.4% performance on GenEval.
  arXiv  Detail & Related papers  (2025-03-27T17:59:46Z)

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.