The development of the transformer-based text-to-image models are impeded by its slow generation and complexity for high-resolution images. In this work, we put forward a solution based on hierarchical transformers and local parallel auto-regressive generation. We pretrain a 6B-parameter transformer with a simple and flexible self-supervised task, Cross-modal general language model (CogLM), and finetune it for fast super-resolution. The new text-to-image system, CogView2, shows very competitive generation compared to concurrent state-of-the-art DALL-E-2, and naturally supports interactive text-guided editing on images.
@article{arxiv.2204.14217,
title = {CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers},
author = {Ming Ding and Wendi Zheng and Wenyi Hong and Jie Tang},
journal= {arXiv preprint arXiv:2204.14217},
year = {2022}
}