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 generative models have attracted rising attention for flexibleimage editing via user-specified descriptions. However, text descriptions aloneare not enough to elaborate the details of subjects, often compromising thesubjects' identity or requiring additional per-subject fine-tuning. Weintroduce a new framework called \textit{Paste, Inpaint and Harmonize viaDenoising} (PhD), which leverages an exemplar image in addition to textdescriptions to specify user intentions. In the pasting step, an off-the-shelfsegmentation model is employed to identify a user-specified subject within anexemplar image which is subsequently inserted into a background image to serveas an initialization capturing both scene context and subject identity in one.To guarantee the visual coherence of the generated or edited image, weintroduce an inpainting and harmonizing module to guide the pre-traineddiffusion model to seamlessly blend the inserted subject into the scenenaturally. As we keep the pre-trained diffusion model frozen, we preserve itsstrong image synthesis ability and text-driven ability, thus achievinghigh-quality results and flexible editing with diverse texts. In ourexperiments, we apply PhD to both subject-driven image editing tasks andexplore text-driven scene generation given a reference subject. Bothquantitative and qualitative comparisons with baseline methods demonstrate thatour approach achieves state-of-the-art performance in both tasks. Morequalitative results can be found at\url{https://sites.google.com/view/phd-demo-page}.

Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model