CogView: Mastering Text-to-Image Generation via TransformersDownload PDF

21 May 2021, 20:44 (edited 26 Oct 2021)NeurIPS 2021 PosterReaders: Everyone
  • Keywords: Transformer, pretraining, generative model, cross-modality
  • TL;DR: CogView: Mastering Text-to-Image Generation via Transformers
  • Abstract: Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e.g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e.g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a recent similar work DALL-E.
  • Supplementary Material: pdf
  • Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
  • Code: https://github.com/THUDM/CogView
13 Replies

Loading