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

Source: [EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics](<https://www.sota2.com/research/paper/6a434da7ba73165dbb743f4d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-01T05:00:18.486Z

Authors: Jiayu Chen, Hengyi Zhang, Maoliang Li, Minyu Li, Zihao Zheng, Xuanzhe Liu, Guojie Luo, Xiang Chen

Published: 2026-06-29T16:51:56.000Z

## Abstract

DiT video generation is latency-intensive due to iterative full-frame denoising, while prior cloud-edge methods largely rely on static inter-step decoupling and cannot leverage inter-frame similarity or adapt to system dynamics. We propose EcoVideo, an entropy-orchestrated framework for dynamic inter-frame decoupling: early-stage self-attention entropy provides a training-free estimate of frame-wise information density for frame selection; a cloud large model denoises sparse high-entropy keyframes; and an edge lightweight model reconstructs the remaining frames via motion-aware interpolation with refinement for temporal stability. EcoVideo further adapts the keyframe budget and edge refinement depth to real-time bandwidth and compute availability, optimizing end-to-end latency under constraints. Experiments on representative DiT video generators show improved quality--efficiency trade-offs and up to 2.9x end-to-end speedup in low-bandwidth, compute-limited edge settings. Code is available at https://github.com/IF-LAB-PKU/EcoVideo.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Video Generation on VBench (Latency and Throughput Metrics)](<https://www.sota2.com/research/sota/video-generation-on-vbench-latency-and-throughput-metrics.md>): Video Generation; VBench; Communication Volume (MB): 0.32.

- [Video Generation on VBench (8 Metrics including Consistency, Quality, and Speedup)](<https://www.sota2.com/research/sota/video-generation-on-vbench-8-metrics-including-consistency-quality-and-speedup.md>): Video Generation; VBench; Subject Consistency: 94.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.30557>)

[PDF](<https://arxiv.org/pdf/2606.30557.pdf>)
