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

The ability to collect a large dataset of human preferences fromtext-to-image users is usually limited to companies, making such datasetsinaccessible to the public. To address this issue, we create a web app thatenables text-to-image users to generate images and specify their preferences.Using this web app we build Pick-a-Pic, a large, open dataset of text-to-imageprompts and real users' preferences over generated images. We leverage thisdataset to train a CLIP-based scoring function, PickScore, which exhibitssuperhuman performance on the task of predicting human preferences. Then, wetest PickScore's ability to perform model evaluation and observe that itcorrelates better with human rankings than other automatic evaluation metrics.Therefore, we recommend using PickScore for evaluating future text-to-imagegeneration models, and using Pick-a-Pic prompts as a more relevant dataset thanMS-COCO. Finally, we demonstrate how PickScore can enhance existingtext-to-image models via ranking.

Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation