mlsanityData to 14 Oct 2026

LLM-Enabled Style and Content Regularization for Personalized Text-to-Image Generation

arXiv 2504.15309 ↗First posted 19 Apr 2025cs.CVcited by 0

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

The personalized text-to-image generation has rapidly advanced with the emergence of Stable Diffusion. Existing methods, which typically fine-tune models using embedded identifiers, often struggle with insufficient stylization and inaccurate image content due to reduced textual controllability. In this paper, we propose style refinement and content preservation strategies. The style refinement strategy leverages the semantic information of visual reasoning prompts and reference images to optimize style embeddings, allowing a more precise and consistent representation of style information. The content preservation strategy addresses the content bias problem by preserving the model's generalization capabilities, ensuring enhanced textual controllability without compromising stylization. Experimental results verify that our approach achieves superior performance in generating consistent and personalized text-to-image outputs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 25 of its 39 references that are in the map. First posted on arXiv 19 Apr 2025.

Builds on

25 of 39 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models4 Sep
  2. 2024Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignment26 Jul
  3. 2024Fast Personalized Text-to-Image Syntheses With Attention Injection17 Mar
  4. 2023ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priors9 Nov
  5. 2023Dense Text-to-Image Generation with Attention Modulation24 Aug
  6. 2023Region-Aware Diffusion for Zero-shot Text-driven Image Editing23 Feb
  7. 2022Multi-Concept Customization of Text-to-Image Diffusion8 Dec
  8. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  10. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 15

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  3. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  4. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,045
  5. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  6. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  7. 2015A Neural Algorithm of Artistic Stylecited by 483
  8. 2023InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuningcited by 345
  9. 2023Break-A-Scene: Extracting Multiple Concepts from a Single Imagecited by 231
  10. 2022Optimizing Prompts for Text-to-Image Generationcited by 207
  11. 2021StyTr2: Image Style Transfer with Transformerscited by 187
  12. 2023Anti-DreamBooth: Protecting users from personalized text-to-image synthesiscited by 120
3 more
  1. 2024Plug-in Diffusion Model for Sequential Recommendationcited by 37
  2. 2024Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalizationcited by 10
  3. 2024MuseumMaker: Continual Style Customization without Catastrophic Forgettingcited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model
  2. 2025Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
  3. 2025StyleBlend: Enhancing Style-Specific Content Creation in Text-to-Image Diffusion Models
  4. 2024Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models
  5. 2024Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning
  6. 2024Block-wise LoRA: Revisiting Fine-grained LoRA for Effective Personalization and Stylization in Text-to-Image Generation
  7. 2024Learning to Customize Text-to-Image Diffusion In Diverse Context
  8. 2023Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion