# Color Bind: Exploring Color Perception in Text-to-Image Models

arXiv: https://arxiv.org/abs/2508.19791 · HTML: https://mlsanity.com/paper/2508.19791/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 30 of 34)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [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)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [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)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022)
- [AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea](https://mlsanity.com/paper/2411.15738/) (2024)
- [Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment](https://mlsanity.com/paper/2306.08877/) (2023)
- [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)
- [Localizing Object-level Shape Variations with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.11306/) (2023)
- [RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths](https://mlsanity.com/paper/2305.18295/) (2023)
- [Cross-Image Attention for Zero-Shot Appearance Transfer](https://mlsanity.com/paper/2311.03335/) (2023)
- [Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing](https://mlsanity.com/paper/2403.03431/) (2024)
- [Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color](https://mlsanity.com/paper/2109.06129/) (2021)
- [Expressive Text-to-Image Generation with Rich Text](https://mlsanity.com/paper/2304.06720/) (2023)
- [Controllable Generation with Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2403.04279/) (2024)
- [Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels](https://mlsanity.com/paper/1512.06974/) (2015)
- [Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding](https://mlsanity.com/paper/1703.10186/) (2017)
- [The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color](https://mlsanity.com/paper/2110.08182/) (2021)
- [ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement](https://mlsanity.com/paper/2407.07197/) (2024)
- [Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding](https://mlsanity.com/paper/2303.12513/) (2023)
- [TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation](https://mlsanity.com/paper/2307.05134/) (2023)

## Built on by (most cited first, 2 of 2)

- [Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion](https://mlsanity.com/paper/2603.18466/) (2026)
- [Paint-Anything: Unified Any-Color Control for Image Generation and Editing](https://mlsanity.com/paper/2609.20816/) (2026)

## Abstract (arXiv)

Text-to-image generation has recently seen remarkable success, granting users with the ability to create high-quality images through the use of text. However, contemporary methods face challenges in capturing the precise semantics conveyed by complex multi-object prompts. Consequently, many works have sought to mitigate such semantic misalignments, typically via inference-time schemes that modify the attention layers of the denoising networks. However, prior work has mostly utilized coarse metrics, such as the cosine similarity between text and image CLIP embeddings, or human evaluations, which are challenging to conduct on a larger-scale. In this work, we perform a case study on colors -- a fundamental attribute commonly associated with objects in text prompts, which offer a rich test bed for rigorous evaluation. Our analysis reveals that pretrained models struggle to generate images that faithfully reflect multiple color attributes-far more so than with single-color prompts-and that neither inference-time techniques nor existing editing methods reliably resolve these semantic misalignments. Accordingly, we introduce a dedicated image editing technique, mitigating the issue of multi-object semantic alignment for prompts containing multiple colors. We demonstrate that our approach significantly boosts performance over a wide range of metrics, considering images generated by various text-to-image diffusion-based techniques.