arXiv:2606. 20506v1 Announce Type: cross Abstract: Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a content reference while adopting the style of a separate style reference.
arXiv:2606. 03792v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) successfully enables personalization in text-to-image generation by adapting pre-trained diffusion models to specific visual concepts and styles.
arXiv:2412.12048v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has become a standard approach for parameter-efficient fine-tuning of image diffusion models, with over 200K models trai...
arXiv:2610.10003v1 Announce Type: new Abstract: Style transfer lacks a reliable evaluation standard: ground truth is inherently ill-defined, and existing automatic metrics often fail to reflect human...
AuthorMix is a lightweight, modular framework for authorship style transfer that uses layer‑wise adapter mixing. It trains individual style‑specific LoRA adapters on a small set of high‑resource authors, enabling rapid adaptation to new target styles with only a few examples. The method achieves the highest combined style‑meaning score among baselines, including GPT‑5.1, and improves meaning preservation, as confirmed by human evaluation.
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,...
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:2606. 26668v1 Announce Type: cross Abstract: Video customization based on Text-to-Video (T2V) models aims to learn specific features from reference data to generate controllable videos.
The paper proposes a three‑stage training method that extracts fine‑grained stylistic representations from a single reference image and injects them into a pretrained generative model without altering its architecture. A style encoder and a style projection layer align these representations with textual cues, enabling controlled stylized image generation. The authors also introduce the Style30k‑captions dataset, which pairs images, style labels, and text descriptions to train the encoder and projection layer.
arXiv:2602.08059v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models can reproduce specific artists visual styles at extremely low cost, raising copyright and deployment safety co...
SafeStyle is a training‑free framework that injects calibrated style residuals into frozen diffusion models for reference‑guided stylization. It estimates style‑supported and content‑associated subspaces from small calibration sets, then transports purified style evidence across adaptive spatial granularity while limiting its influence with a residual‑norm budget. Experiments on texture‑ and geometry‑dominant styles show high DINO style similarity (0.432–0.474) with minimal semantic leakage (0.8%).
arXiv:2606. 16092v1 Announce Type: cross Abstract: Real-world documents combine text with tables, charts, photographs, and diagrams arranged in diverse layouts, yet existing research on multimodal large language models (MLLMs) for document QA predominantly produces text-only responses, underutilizing these visual elements.
Fashion complementary image generation (CIG) aims to create garments that stylistically match a seed item based on user intent, making it a natural multimodal grounding problem where models must inter...