# When Cultures Meet: Multicultural Text-to-Image Generation

arXiv: https://arxiv.org/abs/2502.15972 · HTML: https://mlsanity.com/paper/2502.15972/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 21 Feb 2025.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data](https://mlsanity.com/paper/1911.00359/) (2019)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://mlsanity.com/paper/2412.03304/) (2024)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing](https://mlsanity.com/paper/2407.05600/) (2024)
- [CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark](https://mlsanity.com/paper/2406.05967/) (2024)
- [Survey of Cultural Awareness in Language Models: Text and Beyond](https://mlsanity.com/paper/2411.00860/) (2024)
- [Extracting Cultural Commonsense Knowledge at Scale](https://mlsanity.com/paper/2210.07763/) (2022)
- [A Survey of Race, Racism, and Anti-Racism in NLP](https://mlsanity.com/paper/2106.11410/) (2021)
- [AltDiffusion: A Multilingual Text-to-Image Diffusion Model](https://mlsanity.com/paper/2308.09991/) (2023)
- [Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support](https://mlsanity.com/paper/2401.14688/) (2024)
- [On the Cultural Gap in Text-to-Image Generation](https://mlsanity.com/paper/2307.02971/) (2023)
- [The Power of Many: Multi-Agent Multimodal Models for Cultural Image Captioning](https://mlsanity.com/paper/2411.11758/) (2024)
- [Meta-Cultural Competence: Climbing the Right Hill of Cultural Awareness](https://mlsanity.com/paper/2502.09637/) (2025)

## Built on by (most cited first, 7 of 7)

- [Seeing Culture: A Benchmark for Visual Reasoning and Grounding](https://mlsanity.com/paper/2509.16517/) (2025)
- [coDrawAgents: A Multi-Agent Dialogue Framework for Compositional Image Generation](https://mlsanity.com/paper/2603.12829/) (2026)
- [Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation](https://mlsanity.com/paper/2506.01565/) (2025)
- [When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation](https://mlsanity.com/paper/2605.16716/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [Beyond Translation: Cross-Cultural Meme Transcreation with Vision-Language Models](https://mlsanity.com/paper/2602.02510/) (2026)
- [ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation](https://mlsanity.com/paper/2608.30475/) (2026)

## Abstract (arXiv)

Text-to-image generation models have achieved strong performance in culturally homogeneous settings, yet their ability to generate multicultural scenes, where people and landmarks originate from different cultures, remains largely unexplored. We introduce multicultural text-to-image generation as a new task and present the first benchmark designed to study this setting. Our dataset contains 9,000 images spanning five countries, three age groups, two genders, 25 historical landmarks, and five languages. Using this benchmark, we analyze the behavior of state-of-the-art text-to-image models across multiple dimensions, including alignment, image quality, aesthetics, knowledge, and fairness. As one strategy for composing cultural and demographic information, we explore MosAIG, a Multi-Agent framework that enhances multicultural Image Generation by leveraging LLMs with distinct cultural personas. Our analysis shows that richer prompt composition can improve image quality and cultural grounding compared to simple prompts, while revealing substantial disparities across languages and demographic groups. We release our dataset and code at https://github.com/AIM-SCU/MosAIG.