# A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis

arXiv: https://arxiv.org/abs/2306.14544 · HTML: https://mlsanity.com/paper/2306.14544/

## Key facts

- Cited by 78 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 36 of its 38 references that are in the map.
- First posted on arXiv 26 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 36)

- [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)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [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)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [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)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (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)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis](https://mlsanity.com/paper/1904.01310/) (2019)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Cross-Modal Contrastive Learning for Text-to-Image Generation](https://mlsanity.com/paper/2101.04702/) (2021)
- [Design Guidelines for Prompt Engineering Text-to-Image Generative Models](https://mlsanity.com/paper/2109.06977/) (2021)
- [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022)

## Built on by (most cited first, 30 of 78)

- [Multimodal Foundation Models: From Specialists to General-Purpose Assistants](https://mlsanity.com/paper/2309.10020/) (2023)
- [InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization](https://mlsanity.com/paper/2404.04650/) (2024)
- [PEEKABOO: Interactive Video Generation via Masked-Diffusion](https://mlsanity.com/paper/2312.07509/) (2023)
- [Not All Noises Are Created Equally:Diffusion Noise Selection and Optimization](https://mlsanity.com/paper/2407.14041/) (2024)
- [Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation](https://mlsanity.com/paper/2312.10113/) (2023)
- [CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching](https://mlsanity.com/paper/2404.03653/) (2024)
- [CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image Diffusion Models](https://mlsanity.com/paper/2312.06059/) (2023)
- [SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher](https://mlsanity.com/paper/2408.14176/) (2024)
- [Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis](https://mlsanity.com/paper/2411.07132/) (2024)
- [An Image is Worth Multiple Words: Multi-attribute Inversion for Constrained Text-to-Image Synthesis](https://mlsanity.com/paper/2311.11919/) (2023)
- [LIME: Localized Image Editing via Attention Regularization in Diffusion Models](https://mlsanity.com/paper/2312.09256/) (2023)
- [MC2: Multi-concept Guidance for Customized Multi-concept Generation](https://mlsanity.com/paper/2404.05268/) (2024)
- [Improving Compositional Text-to-image Generation with Large Vision-Language Models](https://mlsanity.com/paper/2310.06311/) (2023)
- [Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers](https://mlsanity.com/paper/2506.07986/) (2025)
- [Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Models](https://mlsanity.com/paper/2312.06712/) (2023)
- [Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2404.07389/) (2024)
- [VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models](https://mlsanity.com/paper/2503.21781/) (2025)
- [Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects](https://mlsanity.com/paper/2411.18936/) (2024)
- [Towards Transformer-Based Aligned Generation with Self-Coherence Guidance](https://mlsanity.com/paper/2503.17675/) (2025)
- [Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else](https://mlsanity.com/paper/2310.07419/) (2023)
- [FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing](https://mlsanity.com/paper/2403.18605/) (2024)
- [Progressive Compositionality in Text-to-Image Generative Models](https://mlsanity.com/paper/2410.16719/) (2024)
- [Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps](https://mlsanity.com/paper/2411.15236/) (2024)
- [Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation](https://mlsanity.com/paper/2411.18301/) (2024)
- [Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation](https://mlsanity.com/paper/2403.19776/) (2024)
- [Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis](https://mlsanity.com/paper/2503.22168/) (2025)
- [Stepwise Credit Assignment for GRPO on Flow-Matching Models](https://mlsanity.com/paper/2603.28718/) (2026)
- [Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesis](https://mlsanity.com/paper/2411.16503/) (2024)
- [Image Generation from Contextually-Contradictory Prompts](https://mlsanity.com/paper/2506.01929/) (2025)
- [Information Theoretic Text-to-Image Alignment](https://mlsanity.com/paper/2405.20759/) (2024)

## Abstract (arXiv)

While recent developments in text-to-image generative models have led to a suite of high-performing methods capable of producing creative imagery from free-form text, there are several limitations. By analyzing the cross-attention representations of these models, we notice two key issues. First, for text prompts that contain multiple concepts, there is a significant amount of pixel-space overlap (i.e., same spatial regions) among pairs of different concepts. This eventually leads to the model being unable to distinguish between the two concepts and one of them being ignored in the final generation. Next, while these models attempt to capture all such concepts during the beginning of denoising (e.g., first few steps) as evidenced by cross-attention maps, this knowledge is not retained by the end of denoising (e.g., last few steps). Such loss of knowledge eventually leads to inaccurate generation outputs. To address these issues, our key innovations include two test-time attention-based loss functions that substantially improve the performance of pretrained baseline text-to-image diffusion models. First, our attention segregation loss reduces the cross-attention overlap between attention maps of different concepts in the text prompt, thereby reducing the confusion/conflict among various concepts and the eventual capture of all concepts in the generated output. Next, our attention retention loss explicitly forces text-to-image diffusion models to retain cross-attention information for all concepts across all denoising time steps, thereby leading to reduced information loss and the preservation of all concepts in the generated output.