让同一主体在不同姿态中保持一致，同时生成多样布局。
CoDi: Subject-Consistent and Pose-Diverse Text-to-Image Generation
- 分两阶段生成：先传身份特征，再精修细节
- 在多个数据集上实现更高的一致性与姿态多样性
- 适合需要角色连贯性的视觉叙事场景
主题一致性生成（SCG）旨在跨多种场景保持主体身份一致，仍是文本到图像（T2I）模型的挑战。现有无训练的SCG方法常以牺牲布局和姿态多样性为代价换取一致性，限制了视觉叙事的表现力。为此，我们提出名为CoDi的主体一致且姿态多样的文本到图像框架。受扩散过程渐进特性的启发——粗结构早期出现，细节点后期优化——CoDi采用两阶段策略：身份传输（IT）与身份精修（IR）。IT在去噪初期通过最优传输实现姿态感知的身份特征迁移，促进主体一致性并保留姿态多样性；IR在后期去噪阶段选择最显著的身份特征以进一步优化主体细节。在主题一致性、姿态多样性和提示保真度上的定性和定量评估表明，CoDi在所有指标上均表现更优，兼具更好的视觉感知效果。代码已公开于 https://github.com/NJU-PCALab/CoDi。
原文摘要 · Abstract (English)
Subject-consistent generation (SCG)-aiming to maintain a consistent subject identity across diverse scenes-remains a challenge for text-to-image (T2I) models. Existing training-free SCG methods often achieve consistency at the cost of layout and pose diversity, hindering expressive visual storytelling. To address the limitation, we propose subject-Consistent and pose-Diverse T2I framework, dubbed as CoDi, that enables consistent subject generation with diverse pose and layout. Motivated by the progressive nature of diffusion, where coarse structures emerge early and fine details are refined later, CoDi adopts a two-stage strategy: Identity Transport (IT) and Identity Refinement (IR). IT operates in the early denoising steps, using optimal transport to transfer identity features to each target image in a pose-aware manner. This promotes subject consistency while preserving pose diversity. IR is applied in the later denoising steps, selecting the most salient identity features to further refine subject details. Extensive qualitative and quantitative results on subject consistency, pose diversity, and prompt fidelity demonstrate that CoDi achieves both better visual perception and stronger performance across all metrics. The code is provided in https://github.com/NJU-PCALab/CoDi.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。