# Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models

Source: [Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models](<https://www.sota2.com/research/paper/68fa75771e209131cea68208>)

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

Data updated: 2025-10-26T03:35:52.229Z

Authors: Chenqian Yan, Songwei Liu, Hongjian Liu, Xurui Peng, Xiaojian Wang, Fangmin Chen, Lean Fu, Xing Mei

Published: 2024-08-13T05:30:41.000Z

## Abstract

Stable Diffusion Models (SDMs) have shown remarkable proficiency in image synthesis. However, their broad application is impeded by their large model sizes and intensive computational requirements, which typically require expensive cloud servers for deployment. On the flip side, while there are many compact models tailored for edge devices that can reduce these demands, they often compromise on semantic integrity and visual quality when compared to full-sized SDMs. To bridge this gap, we introduce Hybrid SD, an innovative, training-free SDMs inference framework designed for edge-cloud collaborative inference. Hybrid SD distributes the early steps of the diffusion process to the large models deployed on cloud servers, enhancing semantic planning. Furthermore, small efficient models deployed on edge devices can be integrated for refining visual details in the later stages. Acknowledging the diversity of edge devices with differing computational and storage capacities, we employ structural pruning to the SDMs U-Net and train a lightweight VAE. Empirical evaluations demonstrate that our compressed models achieve state-of-the-art parameter efficiency (225.8M) on edge devices with competitive image quality. Additionally, Hybrid SD reduces the cloud cost by 66% with edge-cloud collaborative inference.

## 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 (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: 91.8.

- [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): 5.67.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2408.06646>)

[PDF](<https://arxiv.org/pdf/2408.06646.pdf>)
