# Training-Free Layout-to-Image Generation with Marginal Attention Constraints

arXiv: https://arxiv.org/abs/2411.10495 · HTML: https://mlsanity.com/paper/2411.10495/

## Key facts

- Cited by 4 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 34 of its 38 references that are in the map.
- First posted on arXiv 15 Nov 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 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (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)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (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)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (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)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion](https://mlsanity.com/paper/2307.10816/) (2023)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (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)
- [Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation](https://mlsanity.com/paper/2309.14303/) (2023)
- [HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models](https://mlsanity.com/paper/2304.05390/) (2023)
- [Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation](https://mlsanity.com/paper/2403.16990/) (2024)
- [GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation](https://mlsanity.com/paper/2306.04607/) (2023)
- [DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery](https://mlsanity.com/paper/2303.09813/) (2023)
- [HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2410.14324/) (2024)

## Built on by (most cited first, 4 of 4)

- [Control and Realism: Best of Both Worlds in Layout-to-Image without Training](https://mlsanity.com/paper/2506.15563/) (2025)
- [Task-Oriented Data Synthesis and Control-Rectify Sampling for Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2512.16740/) (2025)
- [Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization](https://mlsanity.com/paper/2608.13037/) (2026)
- [Panoptic Scene Program Diffusion Transformer](https://mlsanity.com/paper/2609.31780/) (2026)

## Abstract (arXiv)

Recently, many text-to-image diffusion models have excelled at generating high-resolution images from text but struggle with precise control over spatial composition and object counting. To address these challenges, prior works have developed layout-to-image (L2I) approaches that incorporate layout instructions into text-to-image models. However, existing L2I methods typically require fine-tuning of pre-trained parameters or training additional control modules for diffusion models. In this work, we propose a training-free L2I approach, MAC (Marginal Attention Constrained Generation), which eliminates the need for additional modules or fine-tuning. Specifically, we use text-visual cross-attention feature maps to quantify inconsistencies between the layout of the generated images and the provided instructions, and then compute loss functions to optimize latent features during the diffusion reverse process. To enhance spatial controllability and mitigate semantic failures under complex layout instructions, we leverage pixel-to-pixel correlations in self-attention feature maps to align cross-attention maps and combine three loss functions constrained by boundary attention to update latent features. Comprehensive experimental results on both L2I and non-L2I pretrained diffusion models demonstrate that our method outperforms existing training-free L2I techniques, both quantitatively and qualitatively, in terms of image composition on the DrawBench and HRS benchmarks.