InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation

TL;DR

InstantStyle-Plus introduces a novel, efficient style transfer method for text-to-image generation that preserves content integrity while seamlessly integrating visual styles, addressing limitations of existing diffusion-based approaches.

Contribution

The paper proposes a new approach that deconstructs style transfer into core elements and employs a lightweight, plug-and-play framework with content and style preservation mechanisms.

Findings

Effective content preservation demonstrated in style transfer results.

Seamless style integration with minimal content distortion.

Efficient and lightweight process suitable for real-time applications.

Abstract

Style transfer is an inventive process designed to create an image that maintains the essence of the original while embracing the visual style of another. Although diffusion models have demonstrated impressive generative power in personalized subject-driven or style-driven applications, existing state-of-the-art methods still encounter difficulties in achieving a seamless balance between content preservation and style enhancement. For example, amplifying the style's influence can often undermine the structural integrity of the content. To address these challenges, we deconstruct the style transfer task into three core elements: 1) Style, focusing on the image's aesthetic characteristics; 2) Spatial Structure, concerning the geometric arrangement and composition of visual elements; and 3) Semantic Content, which captures the conceptual meaning of the image. Guided by these principles, we introduce InstantStyle-Plus, an approach that prioritizes the integrity of the original content while seamlessly integrating the target style. Specifically, our method accomplishes style injection through an efficient, lightweight process, utilizing the cutting-edge InstantStyle framework. To reinforce the content preservation, we initiate the process with an inverted content latent noise and a versatile plug-and-play tile ControlNet for preserving the original image's intrinsic layout. We also incorporate a global semantic adapter to enhance the semantic content's fidelity. To safeguard against the dilution of style information, a style extractor is employed as discriminator for providing supplementary style guidance. Codes will be available at https://github.com/instantX-research/InstantStyle-Plus.