Geometric Disentanglement of Text Embeddings for Subject-Consistent Text-to-Image Generation using A Single Prompt

• URL: http://arxiv.org/abs/2512.16443v1
• Date: Thu, 18 Dec 2025 11:55:06 GMT
• Title: Geometric Disentanglement of Text Embeddings for Subject-Consistent Text-to-Image Generation using A Single Prompt
• Authors: Shangxun Li, Youngjung Uh,
• Abstract summary: 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.
• Score: 14.734857939203811
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Text-to-image diffusion models excel at generating high-quality images from natural language descriptions but often fail to preserve subject consistency across multiple outputs, limiting their use in visual storytelling. Existing approaches rely on model fine-tuning or image conditioning, which are computationally expensive and require per-subject optimization. 1Prompt1Story, a training-free approach, concatenates all scene descriptions into a single prompt and rescales token embeddings, but it suffers from semantic leakage, where embeddings across frames become entangled, causing text misalignment. In this paper, we propose a simple yet effective training-free approach that addresses semantic entanglement from a geometric perspective by refining text embeddings to suppress unwanted semantics. Extensive experiments prove that our approach significantly improves both subject consistency and text alignment over existing baselines.

Related papers

• All-in-One Conditioning for Text-to-Image Synthesis [45.22434803596108]
  We propose a novel approach that grounds text-to-image synthesis within the framework of scene graph structures.<n>We introduce a zero-shot, scene graph-based conditioning mechanism that generates soft visual guidance during inference.<n>This enables the model to maintain text-image alignment while supporting lightweight, coherent, and diverse image synthesis.
  arXiv  Detail & Related papers  (2026-02-09T20:16:19Z)
• 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)
• ShapeShift: Towards Text-to-Shape Arrangement Synthesis with Content-Aware Geometric Constraints [13.2441524021269]
  ShapeShift is a text-guided image-to-image translation task that requires rearranging the input set of rigid shapes into non-overlapping configurations.<n>We introduce a content-aware collision resolution mechanism that applies minimal semantically coherent adjustments when overlaps occur.<n>Our approach yields interpretable compositions where spatial relationships clearly embody the textual prompt.
  arXiv  Detail & Related papers  (2025-03-18T20:48:58Z)
• Training-Free Consistent Text-to-Image Generation [80.4814768762066]
  Text-to-image models can portray the same subject across diverse prompts. Existing approaches fine-tune the model to teach it new words that describe specific user-provided subjects. We present ConsiStory, a training-free approach that enables consistent subject generation by sharing the internal activations of the pretrained model.
  arXiv  Detail & Related papers  (2024-02-05T18:42:34Z)
• Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering [118.53208190209517]
  We propose a framework to learn the proper textual descriptions for diffusion models through prompt learning. Our method can effectively learn the prompts to improve the matches between the input text and the generated images.
  arXiv  Detail & Related papers  (2024-01-12T03:46:29Z)
• 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)
• LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts [60.54912319612113]
  Diffusion-based generative models have significantly advanced text-to-image generation but encounter challenges when processing lengthy and intricate text prompts. We present a novel approach leveraging Large Language Models (LLMs) to extract critical components from text prompts. Our evaluation on complex prompts featuring multiple objects demonstrates a substantial improvement in recall compared to baseline diffusion models.
  arXiv  Detail & Related papers  (2023-10-16T17:57:37Z)
• Textual and Visual Prompt Fusion for Image Editing via Step-Wise Alignment [10.82748329166797]
  We propose a framework that integrates a fusion of generated visual references and text guidance into the semantic latent space of a textitfrozen pre-trained diffusion model.<n>Using only a tiny neural network, our framework provides control over diverse content and attributes, driven intuitively by the text prompt.
  arXiv  Detail & Related papers  (2023-08-30T08:40:15Z)
• LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation [121.45667242282721]
  We propose a coarse-to-fine paradigm to achieve layout planning and image generation. Our proposed method outperforms the state-of-the-art models in terms of photorealistic layout and image generation.
  arXiv  Detail & Related papers  (2023-08-09T17:45:04Z)
• 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)

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.