FreeAdapt: Unleashing Diffusion Priors for Ultra-High-Definition Image Restoration

Latent Diffusion Models (LDMs) have recently shown great potential for image restoration owing to their powerful generative priors. However, directly applying them to ultra-high-definition image restoration (UHD-IR) often results in severe global inconsistencies and loss of fine-grained details, primarily caused by patchbased inference and the information bottleneck of the VAE. To overcome these issues, we present FreeAdapt, a plug-and-play framework that unleashes the capability of diffusion priors for UHD-IR. The core of FreeAdapt is a training-free Frequency Feature Synergistic Guidance (FFSG) mechanism, which introduces guidance at each denoising step during inference time. It consists of two modules: 1) Frequency Guidance (FreqG) selectively fuses phase information from a reference image in the frequency domain to enforce structural consistency across the entire image; 2) Feature Guidance (FeatG) injects global contextual information into the self-attention layers of the U-Net, effectively suppressing unrealistic textures in smooth regions and preserving local detail fidelity. In addition, FreeAdapt includes an optional VAE fine-tuning module, where skip connection further enhances the reconstruction of fine-grained textures. Extensive experiments demonstrate that our method achieves superior quantitative performance and visual quality compared to state-of-the-art UHD-IR approaches, and consistently delivers strong gains across multiple LDM-based backbones. Recently, Latent Diffusion Models (LDMs) (Rombach et al., 2022) have shown remarkable potential in low-level vision tasks owing to their powerful generative priors (Lin et al., 2024a; Wu et al., 2024c;b; Yue et al., 2025; Chen et al., 2025a; Sun et al., 2025) . However, directly applying these pre-trained models to UHD-IR faces several technical bottlenecks. First, due to the high computa- RELATED WORK Ultra-High-Definition Image Restoration. UHD-IR has gained increasing attention due to the rapidly growing demand for high-resolution images