CoLay: Controllable Layout Generation through Multi-conditional Latent Diffusion

TL;DR

CoLay is a novel layout generation framework that uses multi-conditional latent diffusion to produce diverse, high-quality layouts aligned with complex user constraints and style properties, enhancing design flexibility.

Contribution

It introduces a multi-conditional diffusion model that integrates various condition types for more expressive and controllable layout generation, surpassing prior methods.

Findings

Outperforms previous models in quality and condition adherence.

Supports multiple modalities including natural language and partial designs.

Enables flexible and complex layout generation.

Abstract

Layout design generation has recently gained significant attention due to its potential applications in various fields, including UI, graphic, and floor plan design. However, existing models face two main challenges that limits their adoption in practice. Firstly, the limited expressiveness of individual condition types used in previous works restricts designers' ability to convey complex design intentions and constraints. Secondly, most existing models focus on generating labels and coordinates, while real layouts contain a range of style properties. To address these limitations, we propose a novel framework, CoLay, that integrates multiple condition types and generates complex layouts with diverse style properties. Our approach outperforms prior works in terms of generation quality and condition satisfaction while empowering users to express their design intents using a flexible combination of modalities, including natural language prompts, layout guidelines, element types, and partially completed designs.