arXiv AI
Disentangle to create: Architecture-level disentangled diffusion model for few-shot Chinese font generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Oct 16
CoDeFont: One-Shot Font Generation via Multi-Scale Factor-Specific Representation Learning
CoDeFont is a new one-shot font generation framework that learns to synthesize target glyphs by transferring style from a single reference glyph while preserving the target’s structure. It achieves this through multi-level style‑content factorization and progressive style‑content reconciliation, creating factor‑specific representations and using a contrastive objective to separate style and content embeddings. The method is evaluated on Bengali and Latin scripts, showing consistent improvements over existing state‑of‑the‑art approaches for both seen and unseen font styles.
Hugging Face Trending Papers
Jun 11
SmartFont: Dynamic Condition Allocation for Few-Shot Font Generation
Few-shot font generation simultaneously requires global structural completeness and fine-grained local style fidelity. Existing methods usually either rely on global content-style modeling, which is robust but imperfectly disentangled, or emphasize component/local modeling, which captures fine details but relies heavily on local priors and reference coverage.
arXiv AI
Jun 12
SmartFont: Dynamic Condition Allocation for Few-Shot Font Generation
arXiv:2606. 13382v1 Announce Type: cross Abstract: Few-shot font generation simultaneously requires global structural completeness and fine-grained local style fidelity.
arXiv Computer Vision
Oct 1
STEPS: Scene Text Editing with Preserved Style Using Diffusion and Contrastive Style Encoding
arXiv:2609.38636v1 Announce Type: new Abstract: We introduce Scene Text Editing with Preserved Style (STEPS), a novel diffusion model architecture for quality text replacement in images. Scene Text E...
arXiv AI
Sep 10
LoGAN: Multilingual Font Localization with Generative Agents
LoGAN is a VLM-based agentic framework designed for few-shot multilingual font localization. It takes a handful of glyphs or logo letters and generates complete character sets across many languages, including CJK, by combining a glyph-level diffusion model, style finetuning, spacing/kerning transfer, and texture expansion. The method outperforms specialized font generators and state‑of‑the‑art image editors in glyph fidelity, style, texture, and kerning consistency on datasets covering more than 27 languages.
arXiv Machine Learning
Sep 15
Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block Training
Abstract‑LoRA introduces a lightweight LoRA training approach that targets specific U‑Net blocks in diffusion models to improve single‑image style transfer. By refining block selection, adding more blocks, and using clustering‑based style abstraction, it better disentangles and balances style and content compared to prior methods like B‑LoRA. Experiments show that the method produces more harmonious artistic images while quantitatively preserving both style and content.