Fast, faithful and photorealistic diffusion-based image super-resolution with enhanced Flow Map models

2026-01-23

AI Summary

This work addresses the challenge in diffusion-based image super-resolution of simultaneously achieving high reconstruction fidelity and photorealistic quality. To this end, we propose FlowMapSR, the first efficient super-resolution framework based on Flow Maps—a variant of Shortcut mechanisms. Our method introduces a novel positive-negative prompt guidance mechanism together with a low-rank adaptation (LoRA)-based adversarial fine-tuning strategy, enabling a single model to unconditionally perform both ×4 and ×8 super-resolution. Experimental results demonstrate that FlowMapSR achieves a superior balance between fidelity and visual realism, outperforming current state-of-the-art methods while maintaining competitive inference efficiency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Prompt Engineering / Prompting

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Diffusion-based image super-resolution (SR) has recently attracted significant attention by leveraging the expressive power of large pre-trained text-to-image diffusion models (DMs). A central practical challenge is resolving the trade-off between reconstruction faithfulness and photorealism. To address inference efficiency, many recent works have explored knowledge distillation strategies specifically tailored to SR, enabling one-step diffusion-based approaches. However, these teacher-student formulations are inherently constrained by information compression, which can degrade perceptual cues such as lifelike textures and depth of field, even with high overall perceptual quality. In parallel, self-distillation DMs, known as Flow Map models, have emerged as a promising alternative for image generation tasks, enabling fast inference while preserving the expressivity and training stability of standard DMs. Building on these developments, we propose FlowMapSR, a novel diffusion-based framework for image super-resolution explicitly designed for efficient inference. Beyond adapting Flow Map models to SR, we introduce two complementary enhancements: (i) positive-negative prompting guidance, based on a generalization of classifier free-guidance paradigm to Flow Map models, and (ii) adversarial fine-tuning using Low-Rank Adaptation (LoRA). Among the considered Flow Map formulations (Eulerian, Lagrangian, and Shortcut), we find that the Shortcut variant consistently achieves the best performance when combined with these enhancements. Extensive experiments show that FlowMapSR achieves a better balance between reconstruction faithfulness and photorealism than recent state-of-the-art methods for both x4 and x8 upscaling, while maintaining competitive inference time. Notably, a single model is used for both upscaling factors, without any scale-specific conditioning or degradation-guided mechanisms.

Problem

• image super-resolution
• diffusion models
• photorealism
• reconstruction faithfulness
• inference efficiency

Innovation

• Flow Map models
• super-resolution
• positive-negative prompting
• LoRA fine-tuning
• photorealistic diffusion