RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing

Excerpt

arXiv:2610.07720v1 Announce Type: cross Abstract: Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existing diffusion transformers commonly encode references as dense visual token grids and jointly process them with global attention, making conditioning increasingly expensive as the number and resolution of references grow. We present RefRoute, a framework that addresses both reference representation cos