mlsanityData to 7 Oct 2026

Divide & Bind Your Attention for Improved Generative Semantic Nursing

arXiv 2307.10864 ↗First posted 20 Jul 2023cs.CV cs.AI cs.CLcited by 80

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

Abstract (arXiv)

Emerging large-scale text-to-image generative models, e.g., Stable Diffusion (SD), have exhibited overwhelming results with high fidelity. Despite the magnificent progress, current state-of-the-art models still struggle to generate images fully adhering to the input prompt. Prior work, Attend & Excite, has introduced the concept of Generative Semantic Nursing (GSN), aiming to optimize cross-attention during inference time to better incorporate the semantics. It demonstrates promising results in generating simple prompts, e.g., "a cat and a dog". However, its efficacy declines when dealing with more complex prompts, and it does not explicitly address the problem of improper attribute binding. To address the challenges posed by complex prompts or scenarios involving multiple entities and to achieve improved attribute binding, we propose Divide & Bind. We introduce two novel loss objectives for GSN: a novel attendance loss and a binding loss. Our approach stands out in its ability to faithfully synthesize desired objects with improved attribute alignment from complex prompts and exhibits superior performance across multiple evaluation benchmarks.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 30 of its 37 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

30 of 37 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models31 Jan
  2. 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis9 Dec
  3. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers2 Nov
  4. 2022MagicMix: Semantic Mixing with Diffusion Models28 Oct
  5. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models26 Oct
  6. 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attention10 Oct
  7. 2022Compositional Visual Generation with Composable Diffusion Models3 Jun
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  9. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  10. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  11. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  12. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
9 more
  1. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  2. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 416
  3. 2022Diffusion Models already have a Semantic Latent Spacecited by 324
  4. 2023Teaching CLIP to Count to Tencited by 194
  5. 2022mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connectionscited by 185
  6. 2023LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluationcited by 85
  7. 2022A very preliminary analysis of DALL-E 2cited by 82
  8. 2022LAVIS: A Library for Language-Vision Intelligencecited by 55
  9. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 35; 2025: 24; 2026: 13.

80 papers.

Sort:

By area:

  1. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 455
  2. 2023Cross-Image Attention for Zero-Shot Appearance Transfercited by 135
  3. 2024InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimizationcited by 123
  4. 2023GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphscited by 96
  5. 2024Controllable Generation with Text-to-Image Diffusion Models: A Surveycited by 82
  6. 2024CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matchingcited by 60
  7. 2023CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image Diffusion Modelscited by 54
  8. 2024SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teachercited by 45
  9. 2024RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customizationcited by 39
  10. 2024MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesiscited by 35
  11. 2024Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesiscited by 35
  12. 2024Alignment of Diffusion Models: Fundamentals, Challenges, and Futurecited by 34
38 more
  1. 2023Quantum circuit synthesis with diffusion modelscited by 33
  2. 2023R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generationcited by 29
  3. 2024MC2: Multi-concept Guidance for Customized Multi-concept Generationcited by 26
  4. 2024SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidancecited by 20
  5. 2023Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Modelscited by 19
  6. 2025Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformerscited by 19
  7. 2024Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrivecited by 18
  8. 2024The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noisecited by 18
  9. 2024A Survey on Quality Metrics for Text-to-Image Generationcited by 17
  10. 2024Non-confusing Generation of Customized Concepts in Diffusion Modelscited by 15
  11. 2024The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generationcited by 14
  12. 2025Towards Transformer-Based Aligned Generation with Self-Coherence Guidancecited by 14
  13. 2024FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editingcited by 12
  14. 2024VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesiscited by 11
  15. 2024Training-free Composite Scene Generation for Layout-to-Image Synthesiscited by 11
  16. 2024Progressive Compositionality in Text-to-Image Generative Modelscited by 11
  17. 2024AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generationcited by 10
  18. 2025Be Decisive: Noise-Induced Layouts for Multi-Subject Generationcited by 10
  19. 2024Contrastive Test-Time Composition of Multiple LoRA Models for Image Generationcited by 9
  20. 2024Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesiscited by 9
  21. 2024Information Theoretic Text-to-Image Alignmentcited by 8
  22. 2024Attention Overlap Is Responsible for The Entity Missing Problem in Text-to-image Diffusion Models!cited by 8
  23. 2025Free-Lunch Color-Texture Disentanglement for Stylized Image Generationcited by 8
  24. 2023ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNetcited by 7
  25. 2024CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesiscited by 7
  26. 2024Isolated Diffusion: Optimizing Multi-Concept Text-to-Image Generation Training-Freely with Isolated Diffusion Guidancecited by 6
  27. 2024Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusioncited by 6
  28. 2024FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weightingcited by 5
  29. 2025Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generationcited by 5
  30. 2025TempoControl: Temporal Attention Guidance for Text-to-Video Modelscited by 5
  31. 2024Obtaining Favorable Layouts for Multiple Object Generationcited by 4
  32. 2024Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Modelscited by 4
  33. 2024FreeCond: Free Lunch in the Input Conditions of Text-Guided Inpaintingcited by 4
  34. 2025Detail++: Training-Free Detail Enhancer for T2I Diffusion Modelscited by 4
  35. 2025Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Imagecited by 3
  36. 2025Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generationcited by 3
  37. 2024SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generationcited by 2
  38. 2025CompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of Artcited by 2

50 most cited of 80 All 80 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
  2. 2024LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation
  3. 2024Towards Better Text-to-Image Generation Alignment via Attention Modulation
  4. 2025CritiFusion: Semantic Critique and Spectral Alignment for Faithful Text-to-Image Generation
  5. 2024PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement
  6. 2023Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models
  7. 2024Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models
  8. 2024Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function