# Color Me Correctly: Bridging Perceptual Color Spaces and Text Embeddings for Improved Diffusion Generation

arXiv: https://arxiv.org/abs/2509.10058 · HTML: https://mlsanity.com/paper/2509.10058/

## Key facts

- Cited by 2 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 11 of its 27 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## 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, 11 of 11)

- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment](https://mlsanity.com/paper/2306.08877/) (2023)
- [InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization](https://mlsanity.com/paper/2404.04650/) (2024)
- [Divide & Bind Your Attention for Improved Generative Semantic Nursing](https://mlsanity.com/paper/2307.10864/) (2023)
- [ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement](https://mlsanity.com/paper/2407.07197/) (2024)
- [FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-training](https://mlsanity.com/paper/2304.05051/) (2023)
- [Color-Emotion Associations in Art: Fuzzy Approach](https://mlsanity.com/paper/2311.18518/) (2023)
- [Towards a Universal Understanding of Color Harmony: Fuzzy Approach](https://mlsanity.com/paper/2310.00791/) (2023)
- [ColorEdit: Training-free Image-Guided Color editing with diffusion model](https://mlsanity.com/paper/2411.10232/) (2024)
- [GenColor: Generative Color-Concept Association in Visual Design](https://mlsanity.com/paper/2503.03236/) (2025)

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

- [NumColor: Precise Numeric Color Control in Text-to-Image Generation](https://mlsanity.com/paper/2603.13547/) (2026)
- [Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion](https://mlsanity.com/paper/2603.18466/) (2026)

## Abstract (arXiv)

Accurate color alignment in text-to-image (T2I) generation is critical for applications such as fashion, product visualization, and interior design, yet current diffusion models struggle with nuanced and compound color terms (e.g., Tiffany blue, lime green, hot pink), often producing images that are misaligned with human intent. Existing approaches rely on cross-attention manipulation, reference images, or fine-tuning but fail to systematically resolve ambiguous color descriptions. To precisely render colors under prompt ambiguity, we propose a training-free framework that enhances color fidelity by leveraging a large language model (LLM) to disambiguate color-related prompts and guiding color blending operations directly in the text embedding space. Our method first employs a large language model (LLM) to resolve ambiguous color terms in the text prompt, and then refines the text embeddings based on the spatial relationships of the resulting color terms in the CIELAB color space. Unlike prior methods, our approach improves color accuracy without requiring additional training or external reference images. Experimental results demonstrate that our framework improves color alignment without compromising image quality, bridging the gap between text semantics and visual generation.