Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization

• URL: http://arxiv.org/abs/2606.02129v1
• Date: Mon, 01 Jun 2026 11:57:10 GMT
• Title: Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization
• Abstract summary: Image customization learns target subjects from reference concept images and generates conditioned images per text prompts.<n>Prevailing methods adopt fine-tuning to pack diverse concept attributes into a unified latent embedding.<n>We propose Equilibrated Diffusion, a frequency-driven approach that disentangles tangled concept features for balanced customization and consistent text-visual matching.
• Score: 31.67012394425792
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image customization learns target subjects from reference concept images and generates conditioned images per text prompts, mainly modifying styles or backgrounds. Prevailing methods adopt fine-tuning to pack diverse concept attributes into a unified latent embedding, yet entangled attributes hinder elimination of irrelevant disturbances from style and background. To address this issue, we propose Equilibrated Diffusion, a frequency-driven approach that disentangles tangled concept features for balanced customization and consistent text-visual matching. Unlike conventional methods learning full concepts with shared embeddings and unified tuning, our work utilizes the inherent link between image frequency components and semantics: low frequencies represent subject content and high frequencies correspond to styles. We decompose concepts in frequency space and optimize each embedding independently. This separate optimization enables the denoiser to capture style detached from subject identity and generalize better to unseen stylistic prompts. Merging multi-frequency embeddings preserves the model's original spatial customization ability. We further deploy mask-guided diffusion to restrict irrelevant background changes and boost text alignment. Residual Reference Attention (RRA) is inserted into spatial attention to retain subject structure and identity consistency. Experiments prove Equilibrated Diffusion exceeds mainstream baselines on subject fidelity and text adherence, verifying our method's superiority.

Related papers

• Redirecting the Flow: Image Customization through Attention Distribution Shift [18.601789249339014]
  Subject-driven image customization aims to generate images that follow textual instructions and preserve the identity of a given reference subject.<n>Existing approaches suffer from limited efficiency, misalignment between extracted reference features and the generative process, and interference from irrelevant information.<n>We propose CustomShift, a dual-branch architecture based on Stable Diffusion 3.<n> Experiments on the DreamBooth and Custom101 benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-06-15T15:44:14Z)
• UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation [65.53694602893042]
  We propose a unified visual conditioning framework that fuses ViT and VAE features before VLM encoding.<n>Experiments on two multi-reference generation benchmarks demonstrate that UniCustom consistently improves subject consistency, instruction following, and compositional fidelity.
  arXiv  Detail & Related papers  (2026-05-12T13:10:05Z)
• Comparison Reveals Commonality: Customized Image Generation through Contrastive Inversion [22.481176245267328]
  We propose Contrastive Inversion, a novel approach that identifies the common concept by comparing the input images without relying on additional information.<n>We train the target token along with the image-wise auxiliary text tokens via contrastive learning, which extracts the well-disentangled true semantics of the target.
  arXiv  Detail & Related papers  (2025-08-11T08:36:29Z)
• Be Decisive: Noise-Induced Layouts for Multi-Subject Generation [56.80513553424086]
  Complex prompts lead to subject leakage, causing inaccuracies in quantities, attributes, and visual features.<n>We introduce a new approach that predicts a spatial layout aligned with the prompt, derived from the initial noise, and refines it throughout the denoising process.<n>Our method employs a small neural network to predict and refine the evolving noise-induced layout at each denoising step.
  arXiv  Detail & Related papers  (2025-05-27T17:54:24Z)
• When StyleGAN Meets Stable Diffusion: a $\mathscr{W}_+$ Adapter for Personalized Image Generation [60.305112612629465]
  Text-to-image diffusion models have excelled in producing diverse, high-quality, and photo-realistic images. We present a novel use of the extended StyleGAN embedding space $mathcalW_+$ to achieve enhanced identity preservation and disentanglement for diffusion models. Our method adeptly generates personalized text-to-image outputs that are not only compatible with prompt descriptions but also amenable to common StyleGAN editing directions.
  arXiv  Detail & Related papers  (2023-11-29T09:05:14Z)
• 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)
• MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask [84.84034179136458]
  A crucial factor leading to the text-image mismatch issue is the inadequate cross-modality relation learning. We propose an adaptive mask, which is conditioned on the attention maps and the prompt embeddings, to dynamically adjust the contribution of each text token to the image features. Our method, termed MaskDiffusion, is training-free and hot-pluggable for popular pre-trained diffusion models.
  arXiv  Detail & Related papers  (2023-09-08T15:53:37Z)
• Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis [59.10787643285506]
  Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. One critical limitation of these models is the low fidelity of generated images with respect to the text description. We propose a new text-to-image algorithm that adds explicit control over spatial-temporal cross-attention in diffusion models.
  arXiv  Detail & Related papers  (2023-04-07T23:49:34Z)
• Diffusion-based Image Translation using Disentangled Style and Content Representation [51.188396199083336]
  Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer. It is often difficult to maintain the original content of the image during the reverse diffusion. We present a novel diffusion-based unsupervised image translation method using disentangled style and content representation. Our experimental results show that the proposed method outperforms state-of-the-art baseline models in both text-guided and image-guided translation tasks.
  arXiv  Detail & Related papers  (2022-09-30T06:44:37Z)

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.