TL;DR
The region-aware diverse stylization (RDS) method is proposed, which generates multiple distinct stylized images from a single-style image without additional training and significantly outperforms state-of-the-art approaches in both fidelity and diversity.
A Structure-Guided Textual Mask Network is designed to predict geometry-aware editing regions by leveraging refined textual structural cues and human-centric priors, where a structural prior reweighting mechanism is introduced to improve localization accuracy.
InstructMixup is proposed, a data augmentation method that constructs challenging yet label-consistent training samples entirely within a single visual sample, and outperforms nine competing augmentation methods, surpassing the strongest baseline across all benchmarks.
A comprehensive hierarchical taxonomy featuring over 1,000 fine-grained edit concepts is established and a dense supervision training strategy that synthesizes multiple non-interfering concepts into single image pairs is proposed that significantly enhances both training efficiency and overall model performance.
An adaptive feature fusion style transfer model based on the U-Net architecture is proposed, which provides a high-fidelity visual information processing framework with potential methodological implications for intelligent image transmission and multi-scale feature representation in advanced engineering systems.
This paper proposes a simple yet effective two-stage training strategy along with a style-strength-aware spline formulation to enable modern Diffusion Transformer-based multi-reference editing models to faithfully preserve the semantic structure of the content image, render strong stylization effects, and smoothly tran...
This work proposes InnoText, a unified DiT-based framework capable of performing both text generation and editing within a single model, and introduces a Font Size-Aware Modulation module to enhance representations across font scales, a Small-Character Aware Augmentation strategy to improve fine-grained fidelity, and a...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
