Enhancing Text-to-Image Generation via End-Edge Collaborative Hybrid Super-Resolution

TL;DR

This paper introduces a collaborative hybrid super-resolution framework that combines diffusion-based and learning-based methods to enhance text-to-image generation quality efficiently at the edge, reducing latency significantly.

Contribution

It proposes an end-edge collaborative approach that adaptively applies different super-resolution models to improve high-resolution image generation with lower latency.

Findings

Reduces service latency by 33% compared to baselines

Maintains competitive image quality with hybrid SR policy

Effectively balances detail recovery and efficiency

Abstract

Artificial Intelligence-Generated Content (AIGC) has made significant strides, with high-resolution text-to-image (T2I) generation becoming increasingly critical for improving users' Quality of Experience (QoE). Although resource-constrained edge computing adequately supports fast low-resolution T2I generations, achieving high-resolution output still faces the challenge of ensuring image fidelity at the cost of latency. To address this, we first investigate the performance of super-resolution (SR) methods for image enhancement, confirming a fundamental trade-off that lightweight learning-based SR struggles to recover fine details, while diffusion-based SR achieves higher fidelity at a substantial computational cost. Motivated by these observations, we propose an end-edge collaborative generation-enhancement framework. Upon receiving a T2I generation task, the system first generates a low-resolution image based on adaptively selected denoising steps and super-resolution scales at the edge side, which is then partitioned into patches and processed by a region-aware hybrid SR policy. This policy applies a diffusion-based SR model to foreground patches for detail recovery and a lightweight learning-based SR model to background patches for efficient upscaling, ultimately stitching the enhanced ones into the high-resolution image. Experiments show that our system reduces service latency by 33% compared with baselines while maintaining competitive image quality.