Creative Blends of Visual Concepts
Zhida Sun, Zhenyao Zhang, Yue Zhang, Min Lu, Dani Lischinski, Daniel Cohen-Or, Hui Huang
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers4
- Vibe Spaces for Creatively Connecting and Expressing Visual ConceptsHuzheng Yang, Katherine Xu, Andrew Lu, Michael D. Grossberg et al.CVPR 2026 · 4 citations
- VLM-Guided Adaptive Negative Prompting for Creative GenerationShelly Golan, Yotam Nitzan, Zongze Wu, Or PatashnikICLR 2026 · 3 citations
- Iconix: Controlling Semantics and Style in Progressive Icon Grids GenerationZhida Sun, Xiaodong Wang, Zhenyao Zhang, Min Lu et al.CHI 2026 · 1 citation
- CREward: A Type-Specific Creativity Reward ModelJiyeon Han, Ali Mahdavi-Amiri, Hao Zhang, Haedong JeongCVPR 2026
Builds on14
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise ExpressionsYunlong Wang, Shuyuan Shen, Brian Y. LimCHI 2023 · 118 citations
- CreativeConnect: Supporting Reference Recombination for Graphic Design Ideation with Generative AIDaEun Choi, Sumin Hong, Jeongeon Park, John Joon Young Chung et al.CHI 2024 · 116 citations
- PromptCharm: Text-to-Image Generation through Multi-modal Prompting and RefinementZhijie Wang, Yuheng Huang, Da Song, Lei Ma et al.CHI 2024 · 111 citations
Related papers
- PopBlends: Strategies for Conceptual Blending with Large Language ModelsSitong Wang, Savvas Petridis, Taeahn Kwon, Xiaojuan Ma et al.CHI 2023 · 57 citations
- GenQuery: Supporting Expressive Visual Search with Generative ModelsKihoon Son, DaEun Choi, Tae Soo Kim, Young-Ho Kim et al.CHI 2024 · 48 citations
- Jigsaw: Supporting Designers to Prototype Multimodal Applications by Chaining AI Foundation ModelsDavid Chuan-En Lin, Nikolas MartelaroCHI 2024 · 22 citations
- IdeationWeb: Tracking the Evolution of Design Ideas in Human-AI Co-CreationHanshu Shen, Lyukesheng Shen, Wenqi Wu, Kejun ZhangCHI 2025 · 24 citations
- Leveraging Multimodal LLM for Inspirational User Interface SearchSeokhyeon Park, Yumin Song, Soohyun Lee, Jaeyoung Kim et al.CHI 2025 · 10 citations
