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 have recently achieved remarkable progress in generatingrealistic images. However, challenges remain in accurately understanding andsynthesizing the layout requirements in the textual prompts. To align thegenerated image with layout instructions, we present a training-free layoutcalibration system SimM that intervenes in the generative process on the flyduring inference time. Specifically, following a "check-locate-rectify"pipeline, the system first analyses the prompt to generate the target layoutand compares it with the intermediate outputs to automatically detect errors.Then, by moving the located activations and making intra- and inter-mapadjustments, the rectification process can be performed with negligiblecomputational overhead. To evaluate SimM over a range of layout requirements,we present a benchmark SimMBench that compensates for the lack of superlativespatial relations in existing datasets. And both quantitative and qualitativeresults demonstrate the effectiveness of the proposed SimM in calibrating thelayout inconsistencies. Our project page is at https://simm-t2i.github.io/SimM.

Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation