# Towards Better Text-to-Image Generation Alignment via Attention Modulation arXiv: https://arxiv.org/abs/2404.13899 ยท HTML: https://mlsanity.com/paper/2404.13899/ ## Key facts - Cited by 9 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 31 of its 35 references that are in the map. - First posted on arXiv 22 Apr 2024. ## 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 31) - [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) - [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014) - [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) - [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023) - [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023) - [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022) - [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022) - [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021) - [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (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) - [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024) - [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022) - [BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion](https://mlsanity.com/paper/2307.10816/) (2023) - [SpaText: Spatio-Textual Representation for Controllable Image Generation](https://mlsanity.com/paper/2211.14305/) (2022) - [ReCo: Region-Controlled Text-to-Image Generation](https://mlsanity.com/paper/2211.15518/) (2022) - [Grounded Text-to-Image Synthesis with Attention Refocusing](https://mlsanity.com/paper/2306.05427/) (2023) - [Dense Text-to-Image Generation with Attention Modulation](https://mlsanity.com/paper/2308.12964/) (2023) - [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://mlsanity.com/paper/2210.00939/) (2022) - [LayoutDM: Discrete Diffusion Model for Controllable Layout Generation](https://mlsanity.com/paper/2303.08137/) (2023) - [ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts](https://mlsanity.com/paper/2210.15257/) (2022) - [Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models](https://mlsanity.com/paper/2305.13921/) (2023) - [LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation](https://mlsanity.com/paper/2302.08908/) (2023) - [LayoutDM: Transformer-based Diffusion Model for Layout Generation](https://mlsanity.com/paper/2305.02567/) (2023) - [Unifying Layout Generation with a Decoupled Diffusion Model](https://mlsanity.com/paper/2303.05049/) (2023) - [Localized Text-to-Image Generation for Free via Cross Attention Control](https://mlsanity.com/paper/2306.14636/) (2023) - [Improving Compositional Text-to-image Generation with Large Vision-Language Models](https://mlsanity.com/paper/2310.06311/) (2023) ## Built on by (most cited first, 9 of 9) - [Alignment of Diffusion Models: Fundamentals, Challenges, and Future](https://mlsanity.com/paper/2409.07253/) (2024) - [Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation](https://mlsanity.com/paper/2504.03193/) (2025) - [Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors](https://mlsanity.com/paper/2503.20211/) (2025) - [3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image](https://mlsanity.com/paper/2503.18853/) (2025) - [RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment](https://mlsanity.com/paper/2603.00483/) (2026) - [Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models](https://mlsanity.com/paper/2410.22775/) (2024) - [GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion](https://mlsanity.com/paper/2510.03110/) (2025) - [Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework](https://mlsanity.com/paper/2605.23891/) (2026) - [M3T2IBench: A Large-Scale Multi-Category, Multi-Instance, Multi-Relation Text-to-Image Benchmark](https://mlsanity.com/paper/2510.23020/) (2025) ## Abstract (arXiv) In text-to-image generation tasks, the advancements of diffusion models have facilitated the fidelity of generated results. However, these models encounter challenges when processing text prompts containing multiple entities and attributes. The uneven distribution of attention results in the issues of entity leakage and attribute misalignment. Training from scratch to address this issue requires numerous labeled data and is resource-consuming. Motivated by this, we propose an attribution-focusing mechanism, a training-free phase-wise mechanism by modulation of attention for diffusion model. One of our core ideas is to guide the model to concentrate on the corresponding syntactic components of the prompt at distinct timesteps. To achieve this, we incorporate a temperature control mechanism within the early phases of the self-attention modules to mitigate entity leakage issues. An object-focused masking scheme and a phase-wise dynamic weight control mechanism are integrated into the cross-attention modules, enabling the model to discern the affiliation of semantic information between entities more effectively. The experimental results in various alignment scenarios demonstrate that our model attain better image-text alignment with minimal additional computational cost.