Salvato in:
Dettagli Bibliografici
Autori principali: Qu, Yadong, Fang, Shancheng, Wang, Yuxin, Wang, Xiaorui, Chen, Zhineng, Xie, Hongtao, Zhang, Yongdong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.09910
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912481065041920
author Qu, Yadong
Fang, Shancheng
Wang, Yuxin
Wang, Xiaorui
Chen, Zhineng
Xie, Hongtao
Zhang, Yongdong
author_facet Qu, Yadong
Fang, Shancheng
Wang, Yuxin
Wang, Xiaorui
Chen, Zhineng
Xie, Hongtao
Zhang, Yongdong
contents Graphic design visually conveys information and data by creating and combining text, images and graphics. Two-stage methods that rely primarily on layout generation lack creativity and intelligence, making graphic design still labor-intensive. Existing diffusion-based methods generate non-editable graphic design files at image level with poor legibility in visual text rendering, which prevents them from achieving satisfactory and practical automated graphic design. In this paper, we propose Instructional Graphic Designer (IGD) to swiftly generate multimodal layers with editable flexibility with only natural language instructions. IGD adopts a new paradigm that leverages parametric rendering and image asset generation. First, we develop a design platform and establish a standardized format for multi-scenario design files, thus laying the foundation for scaling up data. Second, IGD utilizes the multimodal understanding and reasoning capabilities of MLLM to accomplish attribute prediction, sequencing and layout of layers. It also employs a diffusion model to generate image content for assets. By enabling end-to-end training, IGD architecturally supports scalability and extensibility in complex graphic design tasks. The superior experimental results demonstrate that IGD offers a new solution for graphic design.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09910
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IGD: Instructional Graphic Design with Multimodal Layer Generation
Qu, Yadong
Fang, Shancheng
Wang, Yuxin
Wang, Xiaorui
Chen, Zhineng
Xie, Hongtao
Zhang, Yongdong
Computer Vision and Pattern Recognition
Graphic design visually conveys information and data by creating and combining text, images and graphics. Two-stage methods that rely primarily on layout generation lack creativity and intelligence, making graphic design still labor-intensive. Existing diffusion-based methods generate non-editable graphic design files at image level with poor legibility in visual text rendering, which prevents them from achieving satisfactory and practical automated graphic design. In this paper, we propose Instructional Graphic Designer (IGD) to swiftly generate multimodal layers with editable flexibility with only natural language instructions. IGD adopts a new paradigm that leverages parametric rendering and image asset generation. First, we develop a design platform and establish a standardized format for multi-scenario design files, thus laying the foundation for scaling up data. Second, IGD utilizes the multimodal understanding and reasoning capabilities of MLLM to accomplish attribute prediction, sequencing and layout of layers. It also employs a diffusion model to generate image content for assets. By enabling end-to-end training, IGD architecturally supports scalability and extensibility in complex graphic design tasks. The superior experimental results demonstrate that IGD offers a new solution for graphic design.
title IGD: Instructional Graphic Design with Multimodal Layer Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.09910