English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Diffusion models excel at generating photo-realistic images but come withsignificant computational costs in both training and sampling. While varioustechniques address these computational challenges, a less-explored issue isdesigning an efficient and adaptable network backbone for iterative refinement.Current options like U-Net and Vision Transformer often rely onresource-intensive deep networks and lack the flexibility needed for generatingimages at variable resolutions or with a smaller network than used in training.This study introduces LEGO bricks, which seamlessly integrate Local-featureEnrichment and Global-content Orchestration. These bricks can be stacked tocreate a test-time reconfigurable diffusion backbone, allowing selectiveskipping of bricks to reduce sampling costs and generate higher-resolutionimages than the training data. LEGO bricks enrich local regions with an MLP andtransform them using a Transformer block while maintaining a consistentfull-resolution image across all bricks. Experimental results demonstrate thatLEGO bricks enhance training efficiency, expedite convergence, and facilitatevariable-resolution image generation while maintaining strong generativeperformance. Moreover, LEGO significantly reduces sampling time compared toother methods, establishing it as a valuable enhancement for diffusion models.

Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling