# Creative Blends of Visual Concepts

arXiv: https://arxiv.org/abs/2502.16062 · HTML: https://mlsanity.com/paper/2502.16062/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2025.

## Built on by (most cited first, 5 of 5)

- [Vibe Spaces for Creatively Connecting and Expressing Visual Concepts](https://mlsanity.com/paper/2512.14884/) (2025)
- [Blending Concepts with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2506.23630/) (2025)
- [Imagine for Me: Creative Conceptual Blending of Real Images and Text via Blended Attention](https://mlsanity.com/paper/2506.24085/) (2025)
- [CREward: A Type-Specific Creativity Reward Model](https://mlsanity.com/paper/2511.19995/) (2025)
- [Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models](https://mlsanity.com/paper/2609.02502/) (2026)

## Abstract (arXiv)

Visual blends combine elements from two distinct visual concepts into a single, integrated image, with the goal of conveying ideas through imaginative and often thought-provoking visuals. Communicating abstract concepts through visual blends poses a series of conceptual and technical challenges. To address these challenges, we introduce Creative Blends, an AI-assisted design system that leverages metaphors to visually symbolize abstract concepts by blending disparate objects. Our method harnesses commonsense knowledge bases and large language models to align designers' conceptual intent with expressive concrete objects. Additionally, we employ generative text-to-image techniques to blend visual elements through their overlapping attributes. A user study (N=24) demonstrated that our approach reduces participants' cognitive load, fosters creativity, and enhances the metaphorical richness of visual blend ideation. We explore the potential of our method to expand visual blends to include multiple object blending and discuss the insights gained from designing with generative AI.