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

TL;DR

FlowMapSR introduces an efficient diffusion-based super-resolution framework that balances faithfulness and photorealism, leveraging enhanced Flow Map models with prompting guidance and adversarial fine-tuning for superior results.

Contribution

The paper presents FlowMapSR, a novel diffusion-based super-resolution method using Flow Map models with new guidance and fine-tuning techniques, improving inference speed and output quality.

Findings

Outperforms recent state-of-the-art methods in faithfulness and photorealism.

Achieves competitive inference times with a single model for multiple scales.

Demonstrates effectiveness of enhanced Flow Map formulations with proposed techniques.

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.