Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation
Delta-K is proposed, a backbone-agnostic, plug-and-play inference framework that resolves omission by operating directly in the shared cross-attention Key space and significantly improves compositional alignment across both modern DiT and foundational U-Net architectures without requiring spatial masks, auxiliary train...
Zi-Tong Wang, Zijun Shen, Hao Xu et al.
· arXiv.org · 0 citations