Scaling Autoregressive Models for Content-Rich Text-to-Image Generation. (arXiv:2206.10789v1 [cs.CV])

We present the Pathways Autoregressive Text-to-Image (Parti) model, which
generates high-fidelity photorealistic images and supports content-rich
synthesis involving complex compositions and world knowledge. Parti treats
text-to-image generation as a sequence-to-sequence modeling problem, akin to
machine translation, with sequences of image tokens as the target outputs
rather than text tokens in another language. This strategy can naturally tap
into the rich body of prior work on large language models, which have seen
continued advances in capabilities and performance through scaling data …

arxiv autoregressive models cv generation image image generation scaling text text-to-image