Zero-Shot Text-to-Image Generation
arXiv:2102.12092
Abstract
Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part labels or segmentation masks supplied during training. We describe a simple approach for this task based on a transformer that autoregressively models the text and image tokens as a single stream of data. With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.
References in corpus (7)
- Learning Transferable Visual Models From Natural Language Supervision
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Generating Long Sequences with Sparse Transformers
- Jukebox: A Generative Model for Music
- Generating Diverse High-Fidelity Images with VQ-VAE-2
- On the Binding Problem in Artificial Neural Networks
- X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers