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 years have witnessed a rapid growth of deep generative models, withtext-to-image models gaining significant attention from the public. However,existing models often generate images that do not align well with humanpreferences, such as awkward combinations of limbs and facial expressions. Toaddress this issue, we collect a dataset of human choices on generated imagesfrom the Stable Foundation Discord channel. Our experiments demonstrate thatcurrent evaluation metrics for generative models do not correlate well withhuman choices. Thus, we train a human preference classifier with the collecteddataset and derive a Human Preference Score (HPS) based on the classifier.Using HPS, we propose a simple yet effective method to adapt Stable Diffusionto better align with human preferences. Our experiments show that HPSoutperforms CLIP in predicting human choices and has good generalizationcapability toward images generated from other models. By tuning StableDiffusion with the guidance of HPS, the adapted model is able to generateimages that are more preferred by human users. The project page is availablehere: https://tgxs002.github.io/align_sd_web/ .

Human Preference Score: Better Aligning Text-to-Image Models with Human Preference