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

Generative transformers have shown their superiority in synthesizinghigh-fidelity and high-resolution images, such as good diversity and trainingstability. However, they suffer from the problem of slow generation since theyneed to generate a long token sequence autoregressively. To better acceleratethe generative transformers while keeping good generation quality, we proposeLformer, a semi-autoregressive text-to-image generation model. Lformer firstlyencodes an image into $h{\times}h$ discrete tokens, then divides these tokensinto $h$ mirrored L-shape blocks from the top left to the bottom right anddecodes the tokens in a block parallelly in each step. Lformer predicts thearea adjacent to the previous context like autoregressive models thus it ismore stable while accelerating. By leveraging the 2D structure of image tokens,Lformer achieves faster speed than the existing transformer-based methods whilekeeping good generation quality. Moreover, the pretrained Lformer can editimages without the requirement for finetuning. We can roll back to the earlysteps for regeneration or edit the image with a bounding box and a text prompt.

Lformer: Text-to-Image Generation with L-shape Block Parallel Decoding