FontFusion: Enhancing Generative Text in Diffusion Models with Typographic Conditioning

• URL: http://arxiv.org/abs/2606.06066v1
• Date: Thu, 04 Jun 2026 12:07:12 GMT
• Title: FontFusion: Enhancing Generative Text in Diffusion Models with Typographic Conditioning
• Abstract summary: FontFusion is a plug-and-play conditioning framework for Diffusion Transformer (DiT) architectures.<n>Our systematic evaluation of font embedding spaces reveals that a dual encoder combining DeepFont and DINOv2 outperforms any single encoder for typography tasks.
• Score: 6.91163293856906
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Typography generation in diffusion models faces a persistent trade-off: enabling precise font control typically degrades text legibility, while maintaining readability often sacrifices typographic fidelity. We present FontFusion, a plug-and-play conditioning framework for Diffusion Transformer (DiT) architectures that resolves this dilemma through three core innovations: (1) a hierarchical token representation establishing explicit text-font relationships at multiple granularities, (2) position-aware embeddings creating spatial bindings between typography and image content, and (3) a multi-level token dropping strategy improving both computational efficiency and generalization to unseen fonts. Our systematic evaluation of font embedding spaces reveals that a dual encoder combining DeepFont and DINOv2 outperforms any single encoder for typography tasks. FontFusion demonstrates 76% relative improvement on challenging decorative fonts over single-encoder baselines and font consistency gains exceeding approximately 68-76% over unconditioned models, while integrating into existing DiT architectures without retraining.

Related papers

• TextLDM: Language Modeling with Continuous Latent Diffusion [89.69255520673248]
  Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos.<n>We propose TextLDM, which transfers the visual latent diffusion recipe to text generation with minimal architectural modification.
  arXiv  Detail & Related papers  (2026-05-08T13:54:34Z)
• VecGlypher: Unified Vector Glyph Generation with Language Models [49.18215716168074]
  VecGlypher generates high-fidelity vector glyphs directly from text descriptions or image exemplars.<n>VecGlypher autoregressively emits SVG path tokens, avoiding intermediates and a target character.
  arXiv  Detail & Related papers  (2026-02-25T00:27:23Z)
• DA-Font: Few-Shot Font Generation via Dual-Attention Hybrid Integration [12.71388563750518]
  DA-Font is a novel framework which integrates a Dual-Attention Hybrid Module.<n>We show that DA-Font outperforms the state-of-the-art methods across diverse font styles and characters.
  arXiv  Detail & Related papers  (2025-09-20T11:12:15Z)
• GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models [18.15911470339845]
  We introduce a diffusion-based method, termed ourmethod, to generate fonts that vividly embody specific impressions. Our experimental results, conducted on the MyFonts dataset, affirm that this method is capable of producing realistic, vibrant, and high-fidelity fonts.
  arXiv  Detail & Related papers  (2024-08-14T02:26:46Z)
• VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization [52.870638830417]
  We propose a VQGAN-based framework (i.e., VQ-Font) to enhance glyph fidelity through token prior refinement and structure-aware enhancement. Specifically, we pre-train a VQGAN to encapsulate font token prior within a codebook. Subsequently, VQ-Font refines the synthesized glyphs with the codebook to eliminate the domain gap between synthesized and real-world strokes.
  arXiv  Detail & Related papers  (2023-08-27T06:32:20Z)
• Diff-Font: Diffusion Model for Robust One-Shot Font Generation [110.45944936952309]
  We propose a novel one-shot font generation method based on a diffusion model, named Diff-Font. The proposed model aims to generate the entire font library by giving only one sample as the reference. The well-trained Diff-Font is not only robust to font gap and font variation, but also achieved promising performance on difficult character generation.
  arXiv  Detail & Related papers  (2022-12-12T13:51:50Z)
• GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation [30.654807125764965]
  We propose a novel approach, namely GenText, to achieve general artistic text style transfer. Specifically, our work incorporates three different stages, stylization, destylization, and font transfer. Considering the difficult data acquisition of paired artistic text images, our model is designed under the unsupervised setting.
  arXiv  Detail & Related papers  (2022-07-20T04:42:47Z)
• XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation [13.569449355929574]
  We propose a self-supervised cross-modality pre-training strategy and a cross-modality transformer-based encoder. The encoder is conditioned jointly on the glyph image and the corresponding stroke labels. It only requires one reference glyph and achieves the lowest rate of bad cases in the few-shot font generation task 28% lower than the second best.
  arXiv  Detail & Related papers  (2022-04-11T13:34:40Z)
• Scalable Font Reconstruction with Dual Latent Manifolds [55.29525824849242]
  We propose a deep generative model that performs typography analysis and font reconstruction. Our approach enables us to massively scale up the number of character types we can effectively model. We evaluate on the task of font reconstruction over various datasets representing character types of many languages.
  arXiv  Detail & Related papers  (2021-09-10T20:37:43Z)
• A Multi-Implicit Neural Representation for Fonts [79.6123184198301]
  font-specific discontinuities like edges and corners are difficult to represent using neural networks. We introduce textitmulti-implicits to represent fonts as a permutation-in set of learned implict functions, without losing features.
  arXiv  Detail & Related papers  (2021-06-12T21:40:11Z)

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.