CoLay: Controllable Layout Generation through Multi-conditional Latent Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheng, Chin-Yi, Gao, Ruiqi, Huang, Forrest, Li, Yang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913358386561024
author Cheng, Chin-Yi
Gao, Ruiqi
Huang, Forrest
Li, Yang
author_facet Cheng, Chin-Yi
Gao, Ruiqi
Huang, Forrest
Li, Yang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13045
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CoLay: Controllable Layout Generation through Multi-conditional Latent Diffusion
Cheng, Chin-Yi
Gao, Ruiqi
Huang, Forrest
Li, Yang
Human-Computer Interaction
Artificial Intelligence
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.
title CoLay: Controllable Layout Generation through Multi-conditional Latent Diffusion
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2405.13045