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

Text-To-Image (TTI) models, such as DALL-E and StableDiffusion, havedemonstrated remarkable prompt-based image generation capabilities.Multilingual encoders may have a substantial impact on the cultural agency ofthese models, as language is a conduit of culture. In this study, we explorethe cultural perception embedded in TTI models by characterizing culture acrossthree hierarchical tiers: cultural dimensions, cultural domains, and culturalconcepts. Based on this ontology, we derive prompt templates to unlock thecultural knowledge in TTI models, and propose a comprehensive suite ofevaluation techniques, including intrinsic evaluations using the CLIP space,extrinsic evaluations with a Visual-Question-Answer (VQA) model and humanassessments, to evaluate the cultural content of TTI-generated images. Tobolster our research, we introduce the CulText2I dataset, derived from fourdiverse TTI models and spanning ten languages. Our experiments provide insightsregarding Do, What, Which and How research questions about the nature ofcultural encoding in TTI models, paving the way for cross-cultural applicationsof these models.

Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models