Year: 2021
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Ramesh, Aditya, Pavlov, Mikhail, Goh, Gabriel, Gray, Scott, Voss, Chelsea, Radford, Alec, Chen, Mark, Sutskever, Ilya
Institution: OpenAI (United States)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3129576130