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 text-to-image generative models have enabled us to transform our wordsinto vibrant, captivating imagery. The surge of personalization techniques thathas followed has also allowed us to imagine unique concepts in new scenes.However, an intriguing question remains: How can we generate a new, imaginaryconcept that has never been seen before? In this paper, we present the task ofcreative text-to-image generation, where we seek to generate new members of abroad category (e.g., generating a pet that differs from all existing pets). Weleverage the under-studied Diffusion Prior models and show that the creativegeneration problem can be formulated as an optimization process over the outputspace of the diffusion prior, resulting in a set of "prior constraints". Tokeep our generated concept from converging into existing members, weincorporate a question-answering Vision-Language Model (VLM) that adaptivelyadds new constraints to the optimization problem, encouraging the model todiscover increasingly more unique creations. Finally, we show that our priorconstraints can also serve as a strong mixing mechanism allowing us to createhybrids between generated concepts, introducing even more flexibility into thecreative process.

ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints