Skip to content

Similar papers

Open access Feb 2026

Disentangle to create: Architecture-level disentangled diffusion model for few-shot Chinese font generation.

Few-shot Chinese font generation aims to synthesize new characters in a target style using only a handful of reference images. Achieving accurate content rendering and faithful style transfer requires effective disentanglement between content and style. However, most existing approaches achieve only feature-level disen...

Jie Li, Suorong Yang, Jian Zhao et al. · 0 citations
Preprint Oct 2026

CoDeFont: One-Shot Font Generation via Multi-Scale Factor-Specific Representation Learning

One-shot Font Generation (OFG) aims to synthesize a target glyph by transferring the stylistic characteristics of a single reference glyph while preserving the structure of the target character. However, accurately capturing font style from a single reference image remains challenging due to the limited stylistic infor...

R. Chakraborty, Prasun Roy, Saumik Bhattacharya et al. · 0 citations
Preprint Nov 2026

Disentangled Stylized Image Generation via IP-Cross-Attention Rearrangement

With a solid theoretical foundation and pretraining on large-scale datasets, diffusion-based methods have achieved controllable generation leveraging text and image conditions, and generating excellent stylized images is possible using diffusion models. However, previous methods face significant challenges. First, beca...

Bei-Bei Dong, Yueming Lyu, Yue Jiang et al. · 0 citations
Open access Oct 2026

DeStyle: A Unified Decoupled Framework for Style Transfer via Singular Value Purification and Attention-Guided Distillation

A major challenge in training-free image style transfer is to reproduce the artistic characteristics of a reference image while preserving the semantic identity and spatial structure of the content image. Existing methods often struggle to balance content preservation and stylistic expressiveness: aggressive feature in...

Xin-Ying Liu, Tian Xian, Xue-Lei Geng et al. · 0 citations
Conference Sep 2026

Text-driven zero-shot domain adaptation for StyleGAN via CLIP guidance and stylespace regularization

Adapting pretrained StyleGAN generators to novel domains using only text descriptions is challenging due to mode collapse and entangled feature control. We propose a zero-shot adaptation framework that operates primarily in StyleSpace, a highly disentangled control space of StyleGAN. A CLIP directional loss aligns the...

Fei Hou · 0 citations
Nov 2026

Self-learning style transfer via dual-path feature fusion in diffusion models.

Style transfer combines the content of one image with the artistic style of another. Recent advances in diffusion models have improved image generation, but reducing style-content coupling while maintaining high-quality generation remains challenging. We present Self-Learning Style Transfer (SLST), a diffusion-based fr...

Jing-Yi Guo, Ying Li, Shuai-Yu Deng et al. · 0 citations

Related blog posts

Google DeepMind Blog Nov 18, 2026

Genie 4 is now available

We are rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, opening access to our new Genie 4 world model.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.