arXiv:2608. 19719v1 Announce Type: cross Abstract: Reference-based diffusion stylization requires separating target geometry from transferable appearance.
Reference-based diffusion stylization requires separating target geometry from transferable appearance. Existing tuning-based methods often rely on aligned content-style-target triplets or auxiliary visual encoders, which increases data cost and can transfer unintended scene structure from the style reference.
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: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,...
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.
LociArt introduces a unified framework for free‑style local video stylization, allowing precise specification of where to stylize and which style to apply while preserving non‑target content. The core method, GRNStyle, builds on Generative Refinement Networks and uses a polar style‑aware mask to embed style identities as equal‑norm directions within selected regions. An automated pipeline generates paired supervision, leading to the LociArt‑100K dataset and benchmark, which evaluate regional style quality, non‑target preservation, and temporal consistency, and experiments show GRNStyle outperforms existing methods in these aspects.
ContextAnyone is a context‑aware diffusion framework that treats a reference image as an explicitly preserved appearance anchor rather than a simple conditioning signal. By jointly reconstructing the reference image and generating the target video within a shared diffusion transformer, it provides direct supervision for maintaining identity and fine‑grained appearance throughout denoising. The method introduces asymmetric information flow and Gap‑RoPE positional representations to keep the reference stable while allowing selective access by video tokens, and demonstrates improved identity and appearance consistency on an OpenVid‑HD benchmark.
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:2610.08704v1 Announce Type: cross Abstract: Image stylization with latent-diffusion models entangles two independently refined axes: what a region depicts and how it is depicted. Such pipelines...
Artistic image synthesis aims to recreate the expressive visual identity of a target artist, yet existing methods often fail to capture an artist's global style. Conventional style transfer methods transfer the style of one or a few reference artworks to a content image in a One-to-One manner, making them effective for artwork-level stylization but limited in representing the broader stylistic distribution of an artist.
The paper introduces Chameleon, a two‑stage training framework for cross‑domain image compositing that separates style and content representations. It first trains a ChameleonEncoder using Joint Hard Contrastive Learning to disentangle style and content, then applies Spatio‑Temporal Attention Gating within a diffusion transformer to stylize the foreground while preserving its identity. The authors also release ChameleonDataset, the first large‑scale training set for cross‑domain compositing, and demonstrate that Chameleon outperforms existing in‑domain, cross‑domain, and commercial models in both plausibility and stylistic fidelity.
The paper revisits pixel-space diffusion models, showing that a vanilla diffusion transformer can generate directly in pixel space by swapping velocity prediction for clean image prediction. It introduces MFlow, an adaptive parameterization that interpolates between these two prediction modes based on data representation and model capacity, and demonstrates competitive performance on ImageNet, UCF‑101, and text‑to‑image tasks. Additionally, the authors add ConvRefiner, a lightweight convolutional module trained post‑hoc to restore high‑frequency details while preserving FID.
arXiv:2609.39709v1 Announce Type: new Abstract: Recent diffusion-based pipelines have achieved promising progress in image-to-3D synthesis. However, generating high-fidelity details remains challengi...