SOURCE-LINKED INTELLIGENCE

Harnessing Intrinsic Subject-Aware Attention for Controllable Multi-Subject Video Generation

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Multi-subject video generation faces two key challenges: uncontrollable fidelity strength and potential semantic drift. We address these by analyzing the internal mechanisms of Diffusion Transformers (DiTs). We found that certain attention blocks naturally form an Intrinsic Spatial Grounding Map (ISGM) that precisely locates reference subjects. Building on this insight, we propose Dual-phase Intrinsic Attention Leveraging (DIAL), a framework that uses these internal signals for both training and inference. In low-noise stages, we use ISGM to guide the attention mechanism, allowing precise cont

Read original source ↗ Open in workspace

recordType

paper

region

Global