# Grounded Text-to-Image Synthesis with Attention Refocusing

arXiv: https://arxiv.org/abs/2306.05427 · HTML: https://mlsanity.com/paper/2306.05427/

## Key facts

- Cited by 164 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 54 of its 66 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)

## Built on by (most cited first, 30 of 164)

- [MACE: Mass Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2403.06135/) (2024)
- [BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion](https://mlsanity.com/paper/2307.10816/) (2023)
- [Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning](https://mlsanity.com/paper/2307.11410/) (2023)
- [Dense Text-to-Image Generation with Attention Modulation](https://mlsanity.com/paper/2308.12964/) (2023)
- [LLM-grounded Video Diffusion Models](https://mlsanity.com/paper/2309.17444/) (2023)
- [Controllable Generation with Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2403.04279/) (2024)
- [PEEKABOO: Interactive Video Generation via Masked-Diffusion](https://mlsanity.com/paper/2312.07509/) (2023)
- [Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation](https://mlsanity.com/paper/2403.16990/) (2024)
- [MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?](https://mlsanity.com/paper/2407.04842/) (2024)
- [GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning](https://mlsanity.com/paper/2311.12631/) (2023)
- [CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching](https://mlsanity.com/paper/2404.03653/) (2024)
- [CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation](https://mlsanity.com/paper/2412.03859/) (2024)
- [LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models](https://mlsanity.com/paper/2403.11627/) (2024)
- [LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts](https://mlsanity.com/paper/2310.10640/) (2023)
- [VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing](https://mlsanity.com/paper/2502.17258/) (2025)
- [Make It Count: Text-to-Image Generation with an Accurate Number of Objects](https://mlsanity.com/paper/2406.10210/) (2024)
- [MultiBooth: Towards Generating All Your Concepts in an Image from Text](https://mlsanity.com/paper/2404.14239/) (2024)
- [Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models](https://mlsanity.com/paper/2406.11831/) (2024)
- [SceneTeller: Language-to-3D Scene Generation](https://mlsanity.com/paper/2407.20727/) (2024)
- [A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation](https://mlsanity.com/paper/2310.16656/) (2023)
- [AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort](https://mlsanity.com/paper/2311.11243/) (2023)
- [Compositional Text-to-Image Generation with Dense Blob Representations](https://mlsanity.com/paper/2405.08246/) (2024)
- [CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design](https://mlsanity.com/paper/2505.19114/) (2025)
- [MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/2309.13042/) (2023)
- [PALP: Prompt Aligned Personalization of Text-to-Image Models](https://mlsanity.com/paper/2401.06105/) (2024)
- [Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2407.15861/) (2024)
- [Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis](https://mlsanity.com/paper/2411.07132/) (2024)
- [R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation](https://mlsanity.com/paper/2310.08872/) (2023)
- [DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models](https://mlsanity.com/paper/2503.12885/) (2025)
- [Learning Flow Fields in Attention for Controllable Person Image Generation](https://mlsanity.com/paper/2412.08486/) (2024)

## Abstract (arXiv)

Driven by the scalable diffusion models trained on large-scale datasets, text-to-image synthesis methods have shown compelling results. However, these models still fail to precisely follow the text prompt involving multiple objects, attributes, or spatial compositions. In this paper, we reveal the potential causes in the diffusion model's cross-attention and self-attention layers. We propose two novel losses to refocus attention maps according to a given spatial layout during sampling. Creating the layouts manually requires additional effort and can be tedious. Therefore, we explore using large language models (LLM) to produce these layouts for our method. We conduct extensive experiments on the DrawBench, HRS, and TIFA benchmarks to evaluate our proposed method. We show that our proposed attention refocusing effectively improves the controllability of existing approaches.