OmniConsistency：从成对风格化数据中学习风格无关的一致性
OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data
AI总结：
针对扩散模型风格化中的一致性保持和风格退化问题，提出基于DiT的通用一致性插件OmniConsistency，通过上下文学习和两阶段策略，达到与GPT-4o相当的性能。
摘要：
扩散模型显著推进了图像风格化，但仍存在两个核心挑战：（1）在复杂场景中保持一致的风格化，特别是身份、构图和细节；（2）在带有风格LoRA的图像到图像流程中防止风格退化。GPT-4o卓越的风格化一致性凸显了开源方法与专有模型之间的性能差距。为弥合这一差距，我们提出了\textbf{OmniConsistency}，一种利用大规模扩散Transformer（DiTs）的通用一致性插件。OmniConsistency的贡献包括：（1）一种基于对齐图像对训练的上下文一致性学习框架，以实现稳健的泛化；（2）一种两阶段渐进式学习策略，将风格学习与一致性保持解耦，以缓解风格退化；（3）一种完全即插即用的设计，兼容Flux框架下的任意风格LoRA。大量实验表明，OmniConsistency显著提升了视觉连贯性和美学质量，达到了与商业最先进模型GPT-4o相当的性能。
英文摘要：
Diffusion models have advanced image stylization significantly, yet two core challenges persist: (1) maintaining consistent stylization in complex scenes, particularly identity, composition, and fine details, and (2) preventing style degradation in image-to-image pipelines with style LoRAs. GPT-4o's exceptional stylization consistency highlights the performance gap between open-source methods and proprietary models. To bridge this gap, we propose \textbf{OmniConsistency}, a universal consistency plugin leveraging large-scale Diffusion Transformers (DiTs). OmniConsistency contributes: (1) an in-context consistency learning framework trained on aligned image pairs for robust generalization; (2) a two-stage progressive learning strategy decoupling style learning from consistency preservation to mitigate style degradation; and (3) a fully plug-and-play design compatible with arbitrary style LoRAs under the Flux framework. Extensive experiments show that OmniConsistency significantly enhances visual coherence and aesthetic quality, achieving performance comparable to commercial state-of-the-art model GPT-4o.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
