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 cost and attention overhead through two complementary mechanisms. Compact residual conditioning combines low-resolution latent tokens with lightweight residual features extracted from full-resolution pixels, reducing reference token counts while retaining fine-grained appearance cues. Condition routing and attention routing align reference tokens with their assigned target regions and restrict cross-reference interactions, while allowing selective reference access beyond region boundaries for scene integration. We further introduce RefRoute-Data for training many-reference generation models and ManyRef100, a benchmark spanning human, object, and mixed compositions with 10-17 references. After many-reference fine-tuning, RefRoute achieves an overall Weighted-Ref-VIEScore of 36.06 on ManyRef100, compared with 8.88 for FLUX.2-Klein-9B. Separate inference-cost evaluations show substantially slower latency growth as the reference count increases: at 16 references, our 50-step and 4-step configurations achieve $18.3\times$ and $14.2\times$ speedups over their corresponding FLUX baselines, respectively. These results establish compact reference representations and spatially routed attention as an effective approach to scalable many-reference image generation.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
He, W., Zhang, Y., & Tai, Y. W. (2026). RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing. https://omanscience.com/en/articles/refroute-decoupling-conditioning-cost-from-references-via-compact-residual-conditioning-and-spatial-routing
MLA 9
He, Wanning, et al. "RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing." https://omanscience.com/en/articles/refroute-decoupling-conditioning-cost-from-references-via-compact-residual-conditioning-and-spatial-routing.
Chicago (author–date)
He, Wanning, Yuyao Zhang, and Yu-Wing Tai. 2026. "RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing." https://omanscience.com/en/articles/refroute-decoupling-conditioning-cost-from-references-via-compact-residual-conditioning-and-spatial-routing.
Harvard
He, W., Zhang, Y. and Tai, Y. W. (2026) 'RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing', Available at: https://omanscience.com/en/articles/refroute-decoupling-conditioning-cost-from-references-via-compact-residual-conditioning-and-spatial-routing.
Vancouver
He W, Zhang Y, Tai YW. RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing. https://omanscience.com/en/articles/refroute-decoupling-conditioning-cost-from-references-via-compact-residual-conditioning-and-spatial-routing
IEEE
W. He, Y. Zhang, and Y. W. Tai, "RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing," https://omanscience.com/en/articles/refroute-decoupling-conditioning-cost-from-references-via-compact-residual-conditioning-and-spatial-routing.