arXiv AI
Jun 17
Detail++: Training-Free Detail Enhancer for Text-to-Image Diffusion Models
arXiv:2507. 17853v2 Announce Type: replace-cross Abstract: Recent advances in text-to-image (T2I) generation have led to impressive visual results.
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.
Related stories
arXiv AI
Jun 15
Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editing
arXiv:2606. 14125v1 Announce Type: cross Abstract: Inversion-based image editing offers flexible and training-free control but still struggles with inversion accuracy and the trade-off between editing fidelity and background preservation.
arXiv Computer Vision
Sep 11
Overpainting: Localized Context-aware Diffusion Image Editing
The paper introduces "overpainting," a localized, context-aware image editing technique that allows users to specify precise or loose editing regions via a trimap. The method adapts a pretrained diffusion model with joint attention and low‑rank adaptation, incorporating attention‑dropout to balance noise, source, and mask inputs. An automated pipeline generates training data by pairing images from language‑based editing models, curating them, and extracting trimaps, enabling the model to perform a wide range of editing tasks.
arXiv Machine Learning
3d ago
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
Aug 21
Scale-Separated Conditioning for Style-Encoder-Free Diffusion Stylization
arXiv:2608. 19719v1 Announce Type: cross Abstract: Reference-based diffusion stylization requires separating target geometry from transferable appearance.
Hugging Face Trending Papers
Aug 20
Scale-Separated Conditioning for Style-Encoder-Free Diffusion Stylization
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.
Hugging Face Trending Papers
Jul 29
FreeShadow: Training-Free Shadow Removal via Illumination Transfer and Selective Content Preservation in Diffusion Models
Existing supervised and unsupervised shadow removal methods often suffer from limited generalization due to the insufficient diversity of available training datasets, while zero-shot methods tend to produce artifacts and require time-consuming test-time optimization. To address these issues, we propose FreeShadow, a training-free shadow removal method built upon pretrained diffusion models, which exploits diffusion priors for shadow removal without any training or optimization.
Hugging Face Trending Papers
Aug 12
Through Van Gogh's Eyes: Global Style Transfer with Diffusion Mod
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.
arXiv AI
Jun 2
You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
arXiv:2603. 00133v2 Announce Type: replace-cross Abstract: Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement.
arXiv Computer Vision
Aug 24
Anchoring Instruction Outside Mask: Exact Reference Caching for Efficient In-Context Diffusion Transformers
arXiv:2608.21229v1 Announce Type: new Abstract: Omnimodal generation is central to a wide range of content creation and editing applications. In-context conditioning is essential to this paradigm. It...
Hugging Face Trending Papers
Jun 11
DuET: Dual Expert Trajectories for Diffusion Image Editing
Recent diffusion editors perform diverse instruction-based edits while conditioning on the source image at every denoising step. Yet persistent source-image conditioning can limit how fully an edit is executed and how natural the result appears, especially when the target scene diverges substantially from the input.
arXiv Computer Vision
Sep 3
Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing
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.