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

TL;DR

This document outlines ECCV 2022 submission and formatting guidelines, detailing language, length, and metadata requirements to ensure fair, consistent review. It covers the entire lifecycle from initial submission, through confidential, double-blind review, to camera-ready preparation and packaging, including page limits, citation style, and figure/equation formatting. It provides concrete rules for structure, formatting, and anonymization, plus instructions for converting accepted papers into camera-ready uploads with proper author information and supplementary materials. Overall, the guidelines aim to standardize submissions, safeguard review integrity, and streamline publication readiness through detailed templates and checklists.

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.

Figures (1)

• Figure 1: One kernel at $x_s$ ( dotted kernel) or two kernels at $x_i$ and $x_j$ ( left and right) lead to the same summed estimate at $x_s$. This shows a figure consisting of different types of lines. Elements of the figure described in the caption should be set in italics, in parentheses, as shown in this sample caption. The last sentence of a figure caption should generally end without a full stop