Web: https://syncedreview.com/2022/05/05/tsinghua-u-baais-cogview2-achieves-sota-competitive-text-to-image-generation-with-10x-speedups/

May 5, 2022, 3:48 p.m. | Synced

Synced syncedreview.com

In the new paper CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers, Tsinghua University and the Beijing Academy of Artificial Intelligence researchers pretrain a Cross-Modal general Language Model (CogLM) for text and image token prediction and finetune it for fast super-resolution. The resulting CogView2 hierarchical text-to-image system achieves significant speedups while generating images with better quality at comparable resolutions.


The post Tsinghua U & BAAI’s CogView2 Achieves SOTA Competitive Text-to-Image Generation With 10x Speedups first appeared on Synced.

ai artificial intelligence deep-neural-networks image image generation machine learning machine learning & data science ml research sota technology text text-to-image transformers

More from syncedreview.com / Synced

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC

Senior Data Science Writer

@ NannyML | Remote

Director of AI/ML Engineering

@ Armis Industries | Remote (US only), St. Louis, California

Digital Analytics Manager

@ Patagonia | Ventura, California