DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models

• URL: http://arxiv.org/abs/2503.01645v1
• Date: Mon, 03 Mar 2025 15:22:57 GMT
• Title: DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models
• Authors: Zhendong Wang, Jianmin Bao, Shuyang Gu, Dong Chen, Wengang Zhou, Houqiang Li,
• Abstract summary: We present DesignDiffusion, a framework for synthesizing design images from textual descriptions.<n>The proposed framework directly synthesizes textual and visual design elements from user prompts.<n>It utilizes a distinctive character embedding derived from the visual text to enhance the input prompt.
• Score: 115.62816053600085
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions. A primary challenge lies in generating accurate and style-consistent textual and visual content. Existing works in a related task of visual text generation often focus on generating text within given specific regions, which limits the creativity of generation models, resulting in style or color inconsistencies between textual and visual elements if applied to design image generation. To address this issue, we propose an end-to-end, one-stage diffusion-based framework that avoids intricate components like position and layout modeling. Specifically, the proposed framework directly synthesizes textual and visual design elements from user prompts. It utilizes a distinctive character embedding derived from the visual text to enhance the input prompt, along with a character localization loss for enhanced supervision during text generation. Furthermore, we employ a self-play Direct Preference Optimization fine-tuning strategy to improve the quality and accuracy of the synthesized visual text. Extensive experiments demonstrate that DesignDiffusion achieves state-of-the-art performance in design image generation.

Related papers

• Bringing Characters to New Stories: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting [71.29100512700064]
  We present T-Prompter, a training-free method for theme-specific image generation. T-Prompter integrates reference images into generative models, allowing users to seamlessly specify the target theme. Our approach enables consistent story generation, character design, realistic character generation, and style-guided image generation.
  arXiv  Detail & Related papers  (2025-01-26T19:01:19Z)
• Beyond Flat Text: Dual Self-inherited Guidance for Visual Text Generation [17.552733309504486]
  In real-world images, slanted or curved texts, especially those on cans, banners, or badges, appear as frequently as flat texts due to artistic design or layout constraints.<n>We introduce a new training-free framework, STGen, which accurately generates visual texts in challenging scenarios.
  arXiv  Detail & Related papers  (2025-01-10T11:44:59Z)
• Towards Visual Text Design Transfer Across Languages [49.78504488452978]
  We introduce a novel task of Multimodal Style Translation (MuST-Bench) MuST-Bench is a benchmark designed to evaluate the ability of visual text generation models to perform translation across different writing systems. In response, we introduce SIGIL, a framework for multimodal style translation that eliminates the need for style descriptions.
  arXiv  Detail & Related papers  (2024-10-24T15:15:01Z)
• ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models [52.23899502520261]
  We introduce a novel framework named, ARTIST, which incorporates a dedicated textual diffusion model to focus on the learning of text structures specifically.<n>We finetune a visual diffusion model, enabling it to assimilate textual structure information from the pretrained textual model.<n>This disentangled architecture design and training strategy significantly enhance the text rendering ability of the diffusion models for text-rich image generation.
  arXiv  Detail & Related papers  (2024-06-17T19:31:24Z)
• Layout Agnostic Scene Text Image Synthesis with Diffusion Models [42.37340959594495]
  SceneTextGen is a novel diffusion-based model specifically designed to circumvent the need for a predefined layout stage. The novelty of SceneTextGen lies in its integration of three key components: a character-level encoder for capturing detailed typographic properties and a character-level instance segmentation model and a word-level spotting model to address the issues of unwanted text generation and minor character inaccuracies.
  arXiv  Detail & Related papers  (2024-06-03T07:20:34Z)
• Typographic Text Generation with Off-the-Shelf Diffusion Model [7.542892664684078]
  This paper proposes a typographic text generation system to add and modify text on typographic designs. The proposed system is a novel combination of two off-the-shelf methods for diffusion models, ControlNet and Blended Latent Diffusion.
  arXiv  Detail & Related papers  (2024-02-22T06:15:51Z)
• Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model [31.819060415422353]
  Diff-Text is a training-free scene text generation framework for any language. Our method outperforms the existing method in both the accuracy of text recognition and the naturalness of foreground-background blending.
  arXiv  Detail & Related papers  (2023-12-19T15:18:40Z)
• ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priors [105.37795139586075]
  We propose a new task for stylizing'' text-to-image models, namely text-driven stylized image generation. We present a new diffusion model (ControlStyle) via upgrading a pre-trained text-to-image model with a trainable modulation network. Experiments demonstrate the effectiveness of our ControlStyle in producing more visually pleasing and artistic results.
  arXiv  Detail & Related papers  (2023-11-09T15:50:52Z)
• LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts [60.54912319612113]
  Diffusion-based generative models have significantly advanced text-to-image generation but encounter challenges when processing lengthy and intricate text prompts. We present a novel approach leveraging Large Language Models (LLMs) to extract critical components from text prompts. Our evaluation on complex prompts featuring multiple objects demonstrates a substantial improvement in recall compared to baseline diffusion models.
  arXiv  Detail & Related papers  (2023-10-16T17:57:37Z)

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.