Artistic Intelligence: A Diffusion-Based Framework for High-Fidelity Landscape Painting Synthesis

TL;DR

This paper introduces LPGen, a diffusion-based model for high-fidelity landscape painting synthesis that uses decoupled attention and structural control to produce detailed, stylistically coherent artworks.

Contribution

It presents a novel diffusion framework with decoupled cross-attention and a structural controller, advancing AI-generated landscape art with improved fidelity and style control.

Findings

LPGen outperforms existing models in structural accuracy.

The model produces stylistically coherent landscape paintings.

Extensive evaluations validate the effectiveness of the approach.

Abstract

Generating high-fidelity landscape paintings remains a challenging task that requires precise control over both structure and style. In this paper, we present LPGen, a novel diffusion-based model specifically designed for landscape painting generation. LPGen introduces a decoupled cross-attention mechanism that independently processes structural and stylistic features, effectively mimicking the layered approach of traditional painting techniques. Additionally, LPGen proposes a structural controller, a multi-scale encoder designed to control the layout of landscape paintings, striking a balance between aesthetics and composition. Besides, the model is pre-trained on a curated dataset of high-resolution landscape images, categorized by distinct artistic styles, and then fine-tuned to ensure detailed and consistent output. Through extensive evaluations, LPGen demonstrates superior performance in producing paintings that are not only structurally accurate but also stylistically coherent, surpassing current state-of-the-art models. This work advances AI-generated art and offers new avenues for exploring the intersection of technology and traditional artistic practices. Our code, dataset, and model weights will be publicly available.