Learning Interaction between Image and Layout Priors for Joint Image-Layout Generation in Design Templates

• URL: http://arxiv.org/abs/2609.11519v1
• Date: Thu, 10 Sep 2026 13:22:23 GMT
• Title: Learning Interaction between Image and Layout Priors for Joint Image-Layout Generation in Design Templates
• Abstract summary: We propose a model, InterIL, which jointly generates the two modalities, background image and layout, in a single generative process.<n>During training, the image and layout backbones are frozen to maintain and leverage the vast pretrained single-modality prior knowledge.<n>Our model has no design-specific inductive bias, which allows it to better preserve the original characteristics of realistic designs.
• Score: 6.879194169997924
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we address the problem of graphic design template creation, which generates a background image and a layout of foreground elements over the background to form a harmonious composition from an input text. Prior work on graphic design generation mostly adopts a sequential paradigm, where design elements are generated sequentially. We argue that such a sequential scheme falls short of faithfully capturing the dependency between the background and layout (and thus the joint image-layout distribution), which limits the quality of generated design templates. To overcome this limitation, we propose a model, InterIL, which jointly generates the two modalities, background image and layout, in a single generative process. The novel design of our joint model connects the backbones of pretrained image and layout diffusion models with a learnable communication module to explicitly model bidirectional image-layout interaction. During training, the image and layout backbones are frozen to maintain and leverage the vast pretrained single-modality prior knowledge, while only the communication module is updated, so that the model can focus on learning image-layout interaction and thereby better capture the joint image-layout distribution for improved composition harmony. Our model has no design-specific inductive bias, which allows it to better preserve the original characteristics of realistic designs. We further introduce a test-time guidance strategy to enable users to impose their specific preferences on generated results. Our experiments show that, compared with prior approaches, our model can generate significantly better results in terms of image, layout and image-layout harmonization, producing outputs closer to real samples. We also demonstrate the flexibility of our model in enforcing user preferences at inference without retraining.

Related papers

• GMAIL: Generative Modality Alignment for generated Image Learning [51.071351994330605]
  We propose a novel framework for discriminative use of generated images, coined GMAIL, that explicitly treats generated images as a separate modality from real images.<n>Our framework can be easily incorporated with various vision-language models, and we demonstrate its efficacy throughout extensive experiments.
  arXiv  Detail & Related papers  (2026-02-17T05:40:25Z)
• LayoutDiT: Exploring Content-Graphic Balance in Layout Generation with Diffusion Transformer [46.67415676699221]
  We introduce a framework that balances content and graphic features to generate high-quality, visually appealing layouts. Specifically, we design an adaptive factor that optimize the model's awareness of the layout generation space. We also introduce a graphic condition, the saliency bounding box, to bridge the modality difference between images in the visual domain and layouts in the geometric parameter domain.
  arXiv  Detail & Related papers  (2024-07-21T17:58:21Z)
• JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation [49.997839600988875]
  Existing personalization methods rely on finetuning a text-to-image foundation model on a user's custom dataset. We propose Joint-Image Diffusion (jedi), an effective technique for learning a finetuning-free personalization model. Our model achieves state-of-the-art generation quality, both quantitatively and qualitatively, significantly outperforming both the prior finetuning-based and finetuning-free personalization baselines.
  arXiv  Detail & Related papers  (2024-07-08T17:59:02Z)
• Desigen: A Pipeline for Controllable Design Template Generation [69.51563467689795]
  Desigen is an automatic template creation pipeline which generates background images as well as layout elements over the background. We propose two techniques to constrain the saliency distribution and reduce the attention weight in desired regions during the background generation process. Experiments demonstrate that the proposed pipeline generates high-quality templates comparable to human designers.
  arXiv  Detail & Related papers  (2024-03-14T04:32:28Z)
• Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models [67.68871360210208]
  Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, can generate visuals with a high degree of consistency.<n>We propose a novel fine-tuning objective, dubbed Direct Consistency Optimization, which controls the deviation between fine-tuning and pretrained models.<n>We show that our approach achieves better prompt fidelity and subject fidelity than those post-optimized for merging regular fine-tuned models.
  arXiv  Detail & Related papers  (2024-02-19T09:52:41Z)
• Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image Personalization [56.12990759116612]
  Pick-and-Draw is a training-free semantic guidance approach to boost identity consistency and generative diversity for personalization methods. The proposed approach can be applied to any personalized diffusion models and requires as few as a single reference image.
  arXiv  Detail & Related papers  (2024-01-30T05:56:12Z)
• ControlCom: Controllable Image Composition using Diffusion Model [45.48263800282992]
  We propose a controllable image composition method that unifies four tasks in one diffusion model. We also propose a local enhancement module to enhance the foreground details in the diffusion model. The proposed method is evaluated on both public benchmark and real-world data.
  arXiv  Detail & Related papers  (2023-08-19T14:56:44Z)
• LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation [24.694298869398033]
  Our method trains efficiently, generates images with both high perceptual quality and layout alignment. Our method significantly outperforms other 10 generative models based on GANs, VQ-VAE, and diffusion models.
  arXiv  Detail & Related papers  (2023-02-16T14:20:25Z)
• LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer [80.61492265221817]
  Graphic layout designs play an essential role in visual communication. Yet handcrafting layout designs is skill-demanding, time-consuming, and non-scalable to batch production. Generative models emerge to make design automation scalable but it remains non-trivial to produce designs that comply with designers' desires.
  arXiv  Detail & Related papers  (2022-12-19T21:57:35Z)
• Geometry Aligned Variational Transformer for Image-conditioned Layout Generation [38.747175229902396]
  We propose an Image-Conditioned Variational Transformer (ICVT) that autoregressively generates various layouts in an image. First, self-attention mechanism is adopted to model the contextual relationship within layout elements, while cross-attention mechanism is used to fuse the visual information of conditional images. We construct a large-scale advertisement poster layout designing dataset with delicate layout and saliency map annotations.
  arXiv  Detail & Related papers  (2022-09-02T07:19:12Z)
• Meta Internal Learning [88.68276505511922]
  Internal learning for single-image generation is a framework, where a generator is trained to produce novel images based on a single image. We propose a meta-learning approach that enables training over a collection of images, in order to model the internal statistics of the sample image more effectively. Our results show that the models obtained are as suitable as single-image GANs for many common image applications.
  arXiv  Detail & Related papers  (2021-10-06T16:27:38Z)
• Constrained Graphic Layout Generation via Latent Optimization [17.05026043385661]
  We generate graphic layouts that can flexibly incorporate design semantics, either specified implicitly or explicitly by a user. Our approach builds on a generative layout model based on a Transformer architecture, and formulates the layout generation as a constrained optimization problem. We show in the experiments that our approach is capable of generating realistic layouts in both constrained and unconstrained generation tasks with a single model.
  arXiv  Detail & Related papers  (2021-08-02T13:04:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.