Pith. sign in

REVIEW 5 cited by

SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.19151 v1 pith:O26RZXDD submitted 2025-05-25 cs.GR cs.AIcs.CV

SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation

Shenggan Cheng , Yuanxin Wei , Lansong Diao , Yong Liu , Bujiao Chen , Lianghua Huang , Yu Liu , Wenyuan Yu
show 3 more authors
Jiangsu Du Wei Lin Yang You
This is my paper
classification cs.GR cs.AIcs.CV
keywords videoinferencecogvideoxcostdiffusionexistinggenerationlarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Leveraging the diffusion transformer (DiT) architecture, models like Sora, CogVideoX and Wan have achieved remarkable progress in text-to-video, image-to-video, and video editing tasks. Despite these advances, diffusion-based video generation remains computationally intensive, especially for high-resolution, long-duration videos. Prior work accelerates its inference by skipping computation, usually at the cost of severe quality degradation. In this paper, we propose SRDiffusion, a novel framework that leverages collaboration between large and small models to reduce inference cost. The large model handles high-noise steps to ensure semantic and motion fidelity (Sketching), while the smaller model refines visual details in low-noise steps (Rendering). Experimental results demonstrate that our method outperforms existing approaches, over 3$\times$ speedup for Wan with nearly no quality loss for VBench, and 2$\times$ speedup for CogVideoX. Our method is introduced as a new direction orthogonal to existing acceleration strategies, offering a practical solution for scalable video generation.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Speculative Decoding for Autoregressive Video Generation

    cs.CV 2026-04 conditional novelty 7.0

    A training-free speculative decoding method for block-based autoregressive video diffusion uses a quality router on worst-frame ImageReward scores to accept drafter proposals, achieving up to 2.09x speedup at 95.7% qu...

  2. Efficient Video Diffusion Models: Advancements and Challenges

    cs.CV 2026-04 unverdicted novelty 7.0

    A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.

  3. EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics

    cs.CV 2026-06 unverdicted novelty 6.0

    EcoVideo introduces entropy-driven dynamic frame selection for cloud-edge DiT video generation, yielding up to 2.9x speedup with adaptive keyframe budgets.

  4. Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms

    eess.IV 2026-03 unverdicted novelty 6.0

    Video generation models can function as world simulators if efficiency gaps in spatiotemporal modeling are bridged via organized paradigms, architectures, and algorithms.

  5. Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms

    eess.IV 2026-03 conditional novelty 5.0

    In twisted bilayer nodal d-wave superconductors, interlayer hopping creates nodes on the C2 axis and Bogoliubov flat bands when the single-layer Berry connection is parallel to that axis.