Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter

In this work, we present Patch-Adapter, an effective framework for high-resolution text-guided image inpainting. Unlike existing methods limited to lower resolutions, our approach achieves $4 K+$ resolution while maintaining precise content consistency and prompt alignment-two critical challenges in image inpainting that intensify with increasing resolution and texture complexity. Patch-Adapter leverages a two-stage adapter architecture to scale the Diffusion models's resolution from $1 K$ to $4 K+$ without requiring structural overhauls: (1)Dual Context Adapter: Learns coherence between masked and unmasked regions at reduced resolutions to establish global structural consistency. (2)Reference Patch Adapter: Implements a patch-level attention mechanism for full-resolution inpainting, preserving local detail fidelity through adaptive feature fusion. This dual-stage architecture uniquely addresses the scalability gap in high-resolution inpainting by decoupling global semantics from localized refinement. Experiments demonstrate that Patch-Adapter not only resolves artifacts common in large-scale inpainting but also achieves state-of-theart performance on the OpenImages and photo-conceptbucket datasets, outperforming existing methods in both perceptual quality and text-prompt adherence. The code is available at: https://github.com/Roveer/Patch-Based-Adapter