arXiv AI
Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 1
ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images
ReGain is a training‑free correction that improves subject fidelity in text‑to‑image diffusion models personalized with synthetic images. The authors show that fine‑tuning on synthetic images degrades fidelity due to inflated classifier‑free guidance, especially at high frequencies. ReGain measures this inflation per frequency band and scales it down during sampling, closing 51‑64% of the fidelity gap on Stable Diffusion v1.5 and improving performance on SDXL and SD 3.5 while preserving text alignment.
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.
arXiv AI
1d ago
Disentangle to create: Architecture-level disentangled diffusion model for few-shot Chinese font generation
arXiv:2602.18874v2 Announce Type: replace-cross Abstract: Few-shot Chinese font generation aims to synthesize new characters in a target style using only a handful of reference images. Achieving accu...
arXiv Machine Learning
Jun 10
Cost-Aware Routing for Efficient Text-To-Image Generation
arXiv:2506. 14753v3 Announce Type: replace-cross Abstract: Diffusion models are well known for their ability to generate a high-fidelity image for an input prompt through an iterative denoising process.
arXiv AI
Sep 10
MAST: Mask-Guided Attention Control for Training-Free Regional-Multi Style Transfer
MAST (Mask‑Guided Attention Control for Training‑Free Regional‑Multi Style Transfer) is a framework that enables diffusion models to apply multiple reference styles to user‑specified regions of a content image without any training or optimization. It introduces logit‑level attention mass allocation, sharpness‑aware temperature scaling, and discrepancy‑aware detail injection to address mass allocation, selectivity, and detail loss problems in regional‑multi style transfer. Experiments with two to five styles show that MAST outperforms baselines in ArtFID, FID, and R‑FID, achieving high regional style fidelity, content preservation, and scalability.
arXiv Computer Vision
Sep 30
CLeaR: A Unified Framework for Resolving the Leakage-Degradation Dilemma in Style Transfer
arXiv:2609.38136v1 Announce Type: new Abstract: Style transfer aims to render target content in the style of a reference image, but existing methods often suffer from content leakage, where objects,...