AlignedGen: Aligning Style Across Generated Images

• URL: http://arxiv.org/abs/2509.17088v1
• Date: Sun, 21 Sep 2025 14:07:25 GMT
• Title: AlignedGen: Aligning Style Across Generated Images
• Authors: Jiexuan Zhang, Yiheng Du, Qian Wang, Weiqi Li, Yu Gu, Jian Zhang,
• Abstract summary: Diffusion models struggle to maintain style consistency across images conditioned on the same style prompt.<n>We introduce AlignedGen, a training-free framework that enhances style consistency across images generated by DiT models.
• Score: 17.61173470089817
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods attempt to solve this, they are constrained to the U-Net architecture, which not only leads to low-quality results and artifacts like object repetition but also renders them incompatible with superior Diffusion Transformer (DiT). To address these issues, we introduce AlignedGen, a novel training-free framework that enhances style consistency across images generated by DiT models. Our work first reveals a critical insight: naive attention sharing fails in DiT due to conflicting positional signals from improper position embeddings. We introduce Shifted Position Embedding (ShiftPE), an effective solution that resolves this conflict by allocating a non-overlapping set of positional indices to each image. Building on this foundation, we develop Advanced Attention Sharing (AAS), a suite of three techniques meticulously designed to fully unleash the potential of attention sharing within the DiT. Furthermore, to broaden the applicability of our method, we present an efficient query, key, and value feature extraction algorithm, enabling our method to seamlessly incorporate external images as style references. Extensive experimental results validate that our method effectively enhances style consistency across generated images while maintaining precise text-to-image alignment.

Related papers

• DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis [63.59932602411222]
  DMAligner is a diffusion-based framework for image alignment through alignment-oriented view synthesis.<n>We propose a Dynamics-aware Diffusion Training approach for learning conditional image generation.<n>We develop the Dynamic Scene Image Alignment (DSIA) dataset using Blender, which includes 1,033 indoor and outdoor scenes with over 30K image pairs tailored for image alignment.
  arXiv  Detail & Related papers  (2026-02-26T14:00:07Z)
• SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation [9.212970624261272]
  State-of-the-art text-to-image models produce visually impressive results but often struggle with precise alignment to text prompts.<n>We propose a novel approach that learns a high-success-rate distribution conditioned on a target prompt.<n>Our method explicitly models the signal component during the denoising process, offering fine-grained control that mitigates over-optimization.
  arXiv  Detail & Related papers  (2025-08-19T14:31:15Z)
• A Training-Free Style-aligned Image Generation with Scale-wise Autoregressive Model [11.426771898890998]
  We present a training-free style-aligned image generation method that leverages a scale-wise autoregressive model.<n>We show that our method generation quality comparable to competing approaches, significantly improves style alignment, and delivers inference speeds over six times faster than the fastest model.
  arXiv  Detail & Related papers  (2025-04-08T15:39:25Z)
• ZePo: Zero-Shot Portrait Stylization with Faster Sampling [61.14140480095604]
  This paper presents an inversion-free portrait stylization framework based on diffusion models that accomplishes content and style feature fusion in merely four sampling steps. We propose a feature merging strategy to amalgamate redundant features in Consistency Features, thereby reducing the computational load of attention control.
  arXiv  Detail & Related papers  (2024-08-10T08:53:41Z)
• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• Style Aligned Image Generation via Shared Attention [61.121465570763085]
  We introduce StyleAligned, a technique designed to establish style alignment among a series of generated images. By employing minimal attention sharing' during the diffusion process, our method maintains style consistency across images within T2I models. Our method's evaluation across diverse styles and text prompts demonstrates high-quality and fidelity.
  arXiv  Detail & Related papers  (2023-12-04T18:55:35Z)
• Layered Rendering Diffusion Model for Controllable Zero-Shot Image Synthesis [15.76266032768078]
  This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries.<n>We first introduce vision guidance as a foundational spatial cue within the perturbed distribution.<n>We propose a universal framework, Layered Rendering Diffusion (LRDiff), which constructs an image-rendering process with multiple layers.
  arXiv  Detail & Related papers  (2023-11-30T10:36:19Z)
• LoCo: Locally Constrained Training-Free Layout-to-Image Synthesis [24.925757148750684]
  We propose a training-free approach for layout-to-image Synthesis that excels in producing high-quality images aligned with both textual prompts and layout instructions. LoCo seamlessly integrates into existing text-to-image and layout-to-image models, enhancing their performance in spatial control and addressing semantic failures observed in prior methods.
  arXiv  Detail & Related papers  (2023-11-21T04:28:12Z)
• A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning [84.8813842101747]
  Unified Contrastive Arbitrary Style Transfer (UCAST) is a novel style representation learning and transfer framework. We present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature. Our framework consists of three key components, i.e., a parallel contrastive learning scheme for style representation and style transfer, a domain enhancement module for effective learning of style distribution, and a generative network for style transfer.
  arXiv  Detail & Related papers  (2023-03-09T04:35:00Z)
• Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning [84.8813842101747]
  Contrastive Arbitrary Style Transfer (CAST) is a new style representation learning and style transfer method via contrastive learning. Our framework consists of three key components, i.e., a multi-layer style projector for style code encoding, a domain enhancement module for effective learning of style distribution, and a generative network for image style transfer.
  arXiv  Detail & Related papers  (2022-05-19T13:11:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.