CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
This work addresses efficiency and quality issues in text-to-image generation for AI and creative applications, representing an incremental improvement over existing methods.
The authors tackled slow and complex high-resolution text-to-image generation by proposing CogView2, a system based on hierarchical transformers and local parallel auto-regressive generation, which achieves competitive results compared to DALL-E-2 and supports interactive text-guided editing.
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.