InstructG2I: Synthesizing Images from Multimodal Attributed Graphs

TL;DR

InstructG2I introduces a novel graph-conditioned diffusion model for generating images from multimodal attributed graphs, addressing challenges of graph complexity and controllability with innovative sampling and encoding techniques.

Contribution

The paper presents InstructG2I, a new method combining graph structure and multimodal info for controllable image synthesis from attributed graphs.

Findings

Effective image generation demonstrated on three diverse datasets.

Enhanced controllability via graph classifier-free guidance.

Outperforms existing methods in quality and flexibility.

Abstract

In this paper, we approach an overlooked yet critical task Graph2Image: generating images from multimodal attributed graphs (MMAGs). This task poses significant challenges due to the explosion in graph size, dependencies among graph entities, and the need for controllability in graph conditions. To address these challenges, we propose a graph context-conditioned diffusion model called InstructG2I. InstructG2I first exploits the graph structure and multimodal information to conduct informative neighbor sampling by combining personalized page rank and re-ranking based on vision-language features. Then, a Graph-QFormer encoder adaptively encodes the graph nodes into an auxiliary set of graph prompts to guide the denoising process of diffusion. Finally, we propose graph classifier-free guidance, enabling controllable generation by varying the strength of graph guidance and multiple connected edges to a node. Extensive experiments conducted on three datasets from different domains demonstrate the effectiveness and controllability of our approach. The code is available at https://github.com/PeterGriffinJin/InstructG2I.