Skip to yearly menu bar Skip to main content


Zero-Shot Text-to-Image Generation

Aditya Ramesh · Mikhail Pavlov · Gabriel Goh · Scott Gray · Chelsea Voss · Alec Radford · Mark Chen · Ilya Sutskever

Keywords: [ Generative Models ]


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.

Chat is not available.