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

Recent advances in text-to-image diffusion models have achieved remarkablesuccess in generating high-quality, realistic images from textual descriptions.However, these approaches have faced challenges in precisely aligning thegenerated visual content with the textual concepts described in the prompts. Inthis paper, we propose a two-stage coarse-to-fine semantic re-alignment method,named RealignDiff, aimed at improving the alignment between text and images intext-to-image diffusion models. In the coarse semantic re-alignment phase, anovel caption reward, leveraging the BLIP-2 model, is proposed to evaluate thesemantic discrepancy between the generated image caption and the given textprompt. Subsequently, the fine semantic re-alignment stage employs a localdense caption generation module and a re-weighting attention modulation moduleto refine the previously generated images from a local semantic view.Experimental results on the MS-COCO benchmark demonstrate that the proposedtwo-stage coarse-to-fine semantic re-alignment method outperforms otherbaseline re-alignment techniques by a substantial margin in both visual qualityand semantic similarity with the input prompt.

RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment