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 deployment of large-scale text-to-image diffusion models on mobiledevices is impeded by their substantial model size and slow inference speed. Inthis paper, we propose \textbf{MobileDiffusion}, a highly efficienttext-to-image diffusion model obtained through extensive optimizations in botharchitecture and sampling techniques. We conduct a comprehensive examination ofmodel architecture design to reduce redundancy, enhance computationalefficiency, and minimize model's parameter count, while preserving imagegeneration quality. Additionally, we employ distillation and diffusion-GANfinetuning techniques on MobileDiffusion to achieve 8-step and 1-step inferencerespectively. Empirical studies, conducted both quantitatively andqualitatively, demonstrate the effectiveness of our proposed techniques.MobileDiffusion achieves a remarkable \textbf{sub-second} inference speed forgenerating a $512\times512$ image on mobile devices, establishing a new stateof the art.

MobileDiffusion: Subsecond Text-to-Image Generation on Mobile Devices