# Getting it Right: Improving Spatial Consistency in Text-to-Image Models

arXiv: https://arxiv.org/abs/2404.01197 · HTML: https://mlsanity.com/paper/2404.01197/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 69 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 30 of 53)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [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)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (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)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [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)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [Recognize Anything: A Strong Image Tagging Model](https://mlsanity.com/paper/2306.03514/) (2023)

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

- [TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives](https://mlsanity.com/paper/2411.02545/) (2024)
- [From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning](https://mlsanity.com/paper/2504.16080/) (2025)
- [TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation](https://mlsanity.com/paper/2406.08656/) (2024)
- [Scalable Ranked Preference Optimization for Text-to-Image Generation](https://mlsanity.com/paper/2410.18013/) (2024)
- [Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models](https://mlsanity.com/paper/2601.20354/) (2026)
- [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)
- [Attention Overlap Is Responsible for The Entity Missing Problem in Text-to-image Diffusion Models!](https://mlsanity.com/paper/2410.20972/) (2024)
- [Information Theoretic Text-to-Image Alignment](https://mlsanity.com/paper/2405.20759/) (2024)
- [CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2412.13195/) (2024)
- [Towards Self-Improvement of Diffusion Models via Group Preference Optimization](https://mlsanity.com/paper/2505.11070/) (2025)
- [REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models](https://mlsanity.com/paper/2408.02231/) (2024)
- [What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation](https://mlsanity.com/paper/2411.15435/) (2024)
- [SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation](https://mlsanity.com/paper/2603.22228/) (2026)
- [Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models](https://mlsanity.com/paper/2410.22775/) (2024)
- [FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training](https://mlsanity.com/paper/2506.10035/) (2025)
- [GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design](https://mlsanity.com/paper/2508.15227/) (2025)
- [GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis](https://mlsanity.com/paper/2412.06089/) (2024)
- [Role Bias in Diffusion Models: Diagnosing and Mitigating through Intermediate Decomposition](https://mlsanity.com/paper/2503.10037/) (2025)
- [Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image](https://mlsanity.com/paper/2509.02295/) (2025)
- [Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers](https://mlsanity.com/paper/2601.06338/) (2026)
- [SmartSpatial: Enhancing the 3D Spatial Arrangement Capabilities of Stable Diffusion Models and Introducing a Novel 3D Spatial Evaluation Framework](https://mlsanity.com/paper/2501.01998/) (2025)
- [Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models](https://mlsanity.com/paper/2506.23418/) (2025)
- [ESPLoRA: Enhanced Spatial Precision with Low-Rank Adaption in Text-to-Image Diffusion Models for High-Definition Synthesis](https://mlsanity.com/paper/2504.13745/) (2025)
- [Dual Caption Preference Optimization for Diffusion Models](https://mlsanity.com/paper/2502.06023/) (2025)
- [Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models](https://mlsanity.com/paper/2605.06070/) (2026)
- [Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time](https://mlsanity.com/paper/2607.26647/) (2026)
- [MetaSpace: Metamorphic Testing for Spatial Cognition in Embodied Agents](https://mlsanity.com/paper/2608.07533/) (2026)
- [The Plan, Not the Decoder: Diagnosing and Repairing Compositional Failure in Reasoning-Augmented Text-to-Image Generation](https://mlsanity.com/paper/2608.21713/) (2026)
- [Evaluating the Evaluators: Diagnosing Large Multimodal Models for AI-Generated Image Assessment](https://mlsanity.com/paper/2609.37576/) (2026)

## Abstract (arXiv)

One of the key shortcomings in current text-to-image (T2I) models is their inability to consistently generate images which faithfully follow the spatial relationships specified in the text prompt. In this paper, we offer a comprehensive investigation of this limitation, while also developing datasets and methods that support algorithmic solutions to improve spatial reasoning in T2I models. We find that spatial relationships are under-represented in the image descriptions found in current vision-language datasets. To alleviate this data bottleneck, we create SPRIGHT, the first spatially focused, large-scale dataset, by re-captioning 6 million images from 4 widely used vision datasets and through a 3-fold evaluation and analysis pipeline, show that SPRIGHT improves the proportion of spatial relationships in existing datasets. We show the efficacy of SPRIGHT data by showing that using only ~0.25% of SPRIGHT results in a 22% improvement in generating spatially accurate images while also improving FID and CMMD scores. We also find that training on images containing a larger number of objects leads to substantial improvements in spatial consistency, including state-of-the-art results on T2I-CompBench with a spatial score of 0.2133, by fine-tuning on <500 images. Through a set of controlled experiments and ablations, we document additional findings that could support future work that seeks to understand factors that affect spatial consistency in text-to-image models.