High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control

2026-07-07

AI Summary

High-resolution outpainting of artistic images often suffers from unstable global structure, weak layout control, and high inference latency. This work proposes a two-stage diffusion framework: in the first stage, a layout adapter generates a low-resolution global blueprint conditioned on bounding boxes, ensuring structural stability and enabling explicit layout control; in the second stage, high-resolution local regions are synthesized in parallel, guided by the blueprint to preserve global consistency. Built upon a Stable Diffusion inpainting model, the approach integrates forward-diffusion low-frequency-preserving initialization with a parallel patch generation strategy. Evaluated on large-scale artistic datasets, the method achieves significant improvements in visual fidelity and semantic coherence, offers faster inference than existing approaches, and supports flexible user-specified object placement for layout control.

Abstract

Image outpainting extends an image beyond its original borders, requiring seamless style integration and globally coherent scene completion. Building on the success of diffusion models, recent methods have achieved substantial improvements in visual quality. In practice, however, high-resolution outpainting is commonly performed via progressive expansion around a fixed source image, particularly in artwork scenarios. Despite this progress, existing approaches still suffer from three key limitations: (i) the absence of a reliable global planning mechanism, which leads to structural instability and error accumulation at high resolutions; (ii) limited spatial controllability beyond text prompts, making it difficult to place objects at user-specified locations; and (iii) high inference latency caused by inherently sequential patch generation. To address these issues, we propose a global blueprint-guided two-stage diffusion framework for layout-controllable high-resolution outpainting with efficient parallel synthesis. In Stage 1, we generate a low-resolution global blueprint using a layout adapter that injects bounding-box conditions into a Stable Diffusion inpainting backbone, producing a globally consistent structural plan while extracting global guidance features. In Stage 2, we synthesize high-resolution local patches in parallel by injecting the blueprint-derived global guidance and initializing each patch from the blueprint using the low-frequency preservation property of forward diffusion. This design eliminates sequential dependency while maintaining global coherence. Extensive experiments on large-scale artwork datasets demonstrate improved visual fidelity, stronger semantic consistency, and substantially reduced inference time compared to prior baselines, while uniquely supporting explicit layout control for artwork outpainting.

Problem

• image outpainting
• high-resolution
• global coherence
• layout control
• diffusion models

Innovation

• global blueprint
• layout control
• parallel synthesis
• diffusion models
• high-resolution outpainting