383 citations · 736 across the 18 of their papers we have counts for
Showing 2022 · cs.CVShow all
2 papers · 2 filters
cs.CV2022★ 116 cited
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
Wenyi Hong, Ming Ding, Wendi Zheng +2
Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing m…
cs.CV2022★ 121 cited
CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
Ming Ding, Wendi Zheng, Wenyi Hong +1
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…