M-VADER: A Model for Diffusion with Multimodal Context

Abstract: We introduce M-VADER: a diffusion model (DM) for image generation where the output can be specified using arbitrary combinations of images and text. We show how M-VADER enables the generation of images specified using combinations of image and text, and combinations of multiple images. Previously, a number of successful DM image generation algorithms have been introduced that make it possible to specify the output image using a text prompt. Inspired by the success of those models, and led by the notion that language was already developed to describe the elements of visual contexts that humans find most important, we introduce an embedding model closely related to a vision-LLM. Specifically, we introduce the embedding model S-MAGMA: a 13 billion parameter multimodal decoder combining components from an autoregressive vision-LLM MAGMA and biases finetuned for semantic search.