STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model

• URL: http://arxiv.org/abs/2606.10653v1
• Date: Tue, 09 Jun 2026 09:59:09 GMT
• Title: STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model
• Abstract summary: STEDiff is a training-free method designed to enhance semantic representations directly within the text-embedding space.<n>Our method notably improves semantic consistency and generation in complex scenarios.
• Score: 4.685207648946472
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although pretrained text-to-image (T2I) generation models can produce high-quality images, they often fail to faithfully reflect the semantic intent of complex prompts due to stochastic noise and inherent model limitations. This issue frequently manifests as the model overlooking specific objects or failing to correctly bind attributes to their corresponding entities, a challenge referred to as semantic alignment. Unlike existing approaches that rely on computationally expensive fine-tuning or labor-intensive layout priors, we propose STEDiff, a training-free method designed to enhance semantic representations directly within the text-embedding space. Specifically, we introduce a method that primarily leverages the [EOT] token to strengthen the relevant semantics of sub-sentences and then replaces the corresponding tokens in the original prompt. Furthermore, a novel semantic enhancement loss is incorporated to enforce spatial constraints, ensuring that the semantics of each entity are precisely mapped to their respective image regions. Extensive quantitative and qualitative evaluations on the T2I-CompBench demonstrate that our method notably improves semantic consistency and generation integrity in complex scenarios.

Related papers

• TISC: A Text-Driven Image Semantic Communication System for Faithful Reconstruction [12.535011038876815]
  Generative image semantic communication converts an image into a text description and then performs text-to-image reconstruction at the receiver.<n>Existing methods face two critical bottlenecks across image-to-text (I2T) semantic extraction at the transmitter and text-to-image (T2I) semantic reconstruction at the receiver.<n>We propose TISC, a text-driven image semantic communication framework tailored for faithful reconstruction.
  arXiv  Detail & Related papers  (2026-08-17T04:45:02Z)
• Geometric Disentanglement of Text Embeddings for Subject-Consistent Text-to-Image Generation using A Single Prompt [14.734857939203811]
  We propose a training-free approach that addresses semantic entanglement from a subject perspective.<n>Our approach significantly improves both subject consistency and text alignment over existing baselines.
  arXiv  Detail & Related papers  (2025-12-18T11:55:06Z)
• Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers [56.76198904599581]
  Text-to-image diffusion models excel at translating language prompts into implicitly grounding concepts through their cross-modal attention mechanisms.<n>Recent multi-modal diffusion transformers extend this by introducing joint self-attentiond image and text tokens, enabling richer and more scalable cross-modal alignment.<n>We introduce Seg4Diff, a systematic framework for analyzing the attention structures of MM-DiT, with a focus on how specific layers propagate semantic information from text to image.
  arXiv  Detail & Related papers  (2025-09-22T17:59:54Z)
• FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL [78.59912944698992]
  We propose FocusDiff to enhance fine-grained text-image semantic alignment.<n>We construct a new dataset of paired texts and images with similar overall expressions but distinct local semantics.<n>Our approach achieves state-of-the-art performance on existing text-to-image benchmarks and significantly outperforms prior methods on PairComp.
  arXiv  Detail & Related papers  (2025-06-05T18:36:33Z)
• VSC: Visual Search Compositional Text-to-Image Diffusion Model [15.682990658945682]
  We introduce a novel compositional generation method that leverages pairwise image embeddings to improve attribute-object binding.<n>Our approach decomposes complex prompts into sub-prompts, generates corresponding images, and computes visual prototypes that fuse with text embeddings to enhance representation.<n>Our approaches outperform existing compositional text-to-image diffusion models on the benchmark T2I CompBench, achieving better image quality, evaluated by humans, and emerging robustness under scaling number of binding pairs in the prompt.
  arXiv  Detail & Related papers  (2025-05-02T08:31:43Z)
• CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary [55.3680995649415]
  Large-scale text-to-image (T2I) diffusion models have achieved remarkable generative performance about various concepts.<n>With the limitation of privacy and safety in practice, the generative capability concerning NSFW (Not Safe For Work) concepts is undesirable.<n>We propose a framework, which removes the target concepts of T2I diffusion models in the text semantic space.
  arXiv  Detail & Related papers  (2025-01-26T15:39:47Z)
• Localizing Factual Inconsistencies in Attributable Text Generation [74.11403803488643]
  We introduce QASemConsistency, a new formalism for localizing factual inconsistencies in attributable text generation.<n>We show that QASemConsistency yields factual consistency scores that correlate well with human judgments.
  arXiv  Detail & Related papers  (2024-10-09T22:53:48Z)
• 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)
• RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment [112.45442468794658]
  We propose a two-stage coarse-to-fine semantic re-alignment method, named RealignDiff. In the coarse semantic re-alignment phase, a novel caption reward is proposed to evaluate the semantic discrepancy between the generated image caption and the given text prompt. The fine semantic re-alignment stage employs a local dense caption generation module and a re-weighting attention modulation module to refine the previously generated images from a local semantic view.
  arXiv  Detail & Related papers  (2023-05-31T06:59:21Z)
• Marginal Contrastive Correspondence for Guided Image Generation [58.0605433671196]
  Exemplar-based image translation establishes dense correspondences between a conditional input and an exemplar from two different domains. Existing work builds the cross-domain correspondences implicitly by minimizing feature-wise distances across the two domains. We design a Marginal Contrastive Learning Network (MCL-Net) that explores contrastive learning to learn domain-invariant features for realistic exemplar-based image translation.
  arXiv  Detail & Related papers  (2022-04-01T13:55:44Z)
• Image Inpainting Guided by Coherence Priors of Semantics and Textures [62.92586889409379]
  We introduce coherence priors between the semantics and textures which make it possible to concentrate on completing separate textures in a semantic-wise manner. We also propose two coherence losses to constrain the consistency between the semantics and the inpainted image in terms of the overall structure and detailed textures.
  arXiv  Detail & Related papers  (2020-12-15T02:59:37Z)

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.