Recent unified models such as Bagel demonstrate that paired image-edit data can effectively align multiple visual tasks within a single diffusion transformer. However, these models remain limited to single-condition inputs and lack the flexibility needed to synthesize results from multiple heterogeneous sources. We present SIGMA (Selective-Interleaved Generation with Multi-Attribute Tokens), a unified post-training framework that enables interleaved multi-condition generation within diffusion transformers. SIGMA introduces selective multi-attribute tokens, including style, content, subject, and identity tokens, which allow the model to interpret and compose multiple visual conditions in an interleaved text-image sequence. Through post-training on the Bagel unified backbone with 700K interleaved examples, SIGMA supports compositional editing, selective attribute transfer, and fine-grained multimodal alignment. Extensive experiments show that SIGMA improves controllability, cross-condition consistency, and visual quality across diverse editing and generation tasks, with substantial gains over Bagel on compositional tasks.

翻译：近期如Bagel等统一模型表明，配对图像编辑数据能有效将多种视觉任务对齐至单个扩散Transformer中。然而，这些模型仍局限于单条件输入，缺乏从多个异构源合成结果的灵活性。我们提出SIGMA（基于多属性标记的选择性交错生成），这是一种统一的微调后训练框架，可在扩散Transformer中实现交错多条件生成。SIGMA引入了选择性多属性标记，包括风格、内容、主体和身份标记，使模型能够解析并组合交错图文序列中的多种视觉条件。通过在Bagel统一骨干网络上使用70万个交错样本进行微调后训练，SIGMA支持组合编辑、选择性属性迁移和细粒度多模态对齐。大量实验表明，SIGMA在多样化编辑与生成任务中显著提升了可控性、跨条件一致性和视觉质量，在组合任务上较Bagel实现了实质性提升。