CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

TL;DR

CreatiLayout introduces a multimodal diffusion transformer with a siamese architecture and a large-scale dataset for precise, controllable, and creative layout-to-image generation, leveraging layout planning and optimization.

Contribution

The paper presents SiamLayout, a novel multimodal diffusion transformer with a siamese structure for layout guidance, and introduces LayoutSAM dataset and Layout Designer for enhanced layout-to-image generation.

Findings

Effective integration of layout guidance into MM-DiT.

Large-scale LayoutSAM dataset with 2.7 million image-text pairs.

Improved quality and controllability in layout-to-image generation.

Abstract

Diffusion models have been recognized for their ability to generate images that are not only visually appealing but also of high artistic quality. As a result, Layout-to-Image (L2I) generation has been proposed to leverage region-specific positions and descriptions to enable more precise and controllable generation. However, previous methods primarily focus on UNet-based models (\eg SD1.5 and SDXL), and limited effort has explored Multimodal Diffusion Transformers (MM-DiTs), which have demonstrated powerful image generation capabilities. Enabling MM-DiT for layout-to-image generation seems straightforward but is challenging due to the complexity of how layout is introduced, integrated, and balanced among multiple modalities. To this end, we explore various network variants to efficiently incorporate layout guidance into MM-DiT, and ultimately present SiamLayout. To inherit the advantages of MM-DiT, we use a separate set of network weights to process the layout, treating it as equally important as the image and text modalities. Meanwhile, to alleviate the competition among modalities, we decouple the image-layout interaction into a siamese branch alongside the image-text one and fuse them in the later stage. Moreover, we contribute a large-scale layout dataset, named LayoutSAM, which includes 2.7 million image-text pairs and 10.7 million entities. Each entity is annotated with a bounding box and a detailed description. We further construct the LayoutSAM-Eval benchmark as a comprehensive tool for evaluating the L2I generation quality. Finally, we introduce the Layout Designer, which taps into the potential of large language models in layout planning, transforming them into experts in layout generation and optimization. These components form CreatiLayout -- a systematic solution that integrates the layout model, dataset, and planner for creative layout-to-image generation.