---
title: "Navigating Cultural Chasms — paper by Ventura et al. (2025)"
description: "The work offers a systematic way to inspect cultural representation in TTI systems and supports… 37 references, cited by 19 papers here."
authors: ["Mor Ventura", "Eyal Ben-David", "Anna Korhonen", "Roi Reichart"]
year: 2025
venue: "Transactions of the Association for Computational Linguistics"
source: "https://aclanthology.org/2025.tacl-1.10/"
doi: "10.1162/tacl_a_00732"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/ventura-2025-navigating-cultural-chasms-exploring-unlocking/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ventura-2025-navigating-cultural-chasms-exploring-unlocking/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/) / Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models

# Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models

**Authors:** Mor Ventura, Eyal Ben-David, [Anna Korhonen](https://md.research.elamur.ai/free/en/authors/anna-korhonen/) and [Roi Reichart](https://md.research.elamur.ai/free/en/authors/roi-reichart/) · **Year:** 2025 · **Venue:** [Transactions of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/tacl/) ([Transactions of the Association for Computational Linguistics (TACL) 2025](https://md.research.elamur.ai/free/en/venues/tacl/2025/)) · **Publisher:** [The MIT Press](https://md.research.elamur.ai/free/en/publishers/the-mit-press/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.tacl-1.10/) · [PDF](https://aclanthology.org/2025.tacl-1.10.pdf) · [DOI 10.1162/tacl\_a\_00732](https://doi.org/10.1162/tacl_a_00732) · [OpenAlex](https://openalex.org/W4410490964)

**Citations:** 6 citations (OpenAlex, 2026-10-14) · [19](https://md.research.elamur.ai/free/en/papers/ventura-2025-navigating-cultural-chasms-exploring-unlocking/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Text-to-image (TTI) generators increasingly accept prompts in many languages. Because language carries culture, the authors ask whether these models hold cultural knowledge and how it can be drawn out. They split culture into a three-level ontology built from Hofstede, Rokeach and the World Values Survey: broad cultural dimensions, cultural domains (e.g., Religion, Economy, Security) and 200 concrete cultural concepts. From this ontology they derive prompt templates that vary language use. Options include translating the whole prompt, translating only the concept, adding a nationality to an English prompt, or appending gibberish in a target script. They also release CulText2I, a dataset of images from six TTI models across ten languages. Evaluation combines intrinsic CLIP-space measures, extrinsic probing with VQA models (BLIP, GPT-4 Vision) and human judgments. The findings show that TTI models do capture cultural signals. The multilingual text encoder plays a major role, and prompt design strongly shapes how much culture appears in the images. The work offers a systematic way to inspect cultural representation in TTI systems and supports cross-cultural applications.

## Key points
- CulText2I draws on prompts in ten languages and images from DALL-E, DeepFloyd, AltDiffusion, two StableDiffusion versions (2.1v and 1.4v), and Llavi-Bridge, which couples Llama with an SD 1.4 UNet. Code and data are on GitHub (venturamor/CulText-2-I).
- The research questions follow a Do/What/Which/How structure:
  - whether culture is encoded,
  - which cultural dimensions are present,
  - which cultures the models treat as similar,
  - how cultural knowledge can be unlocked.
- On the national-association (XNA) task, GPT-4 Vision scored a mean of 69.36%, against 45.13% for BLIP on the same subset, and matched human answers in 70% of cases.
- Natural images from Google search allowed national origin to be detected about 25% better on average than TTI images. This serves as an upper bound and suggests TTI models have room to encode culture better.
- A Conceptor analysis of the concept "king" exposed language-specific hidden tokens:
  - Arabic: tokens linked to art and poetry,
  - German: hierarchy and music,
  - Russian: political terms.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Cambridge](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) — University, Cambridge, United Kingdom · 256 works · 123,373 citations
- [Technion – Israel Institute of Technology](https://md.research.elamur.ai/free/en/universities/technion-israel-institute-of-technology/) — University, Haifa, Israel · 54 works · 7,237 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

🧭 Topics (1): [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works

## Cite

Cite as: Mor Ventura, Eyal Ben-David, Anna Korhonen and Roi Reichart. 2025. Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models. Transactions of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@article{ventura2025navigating,
  title = {{Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models}},
  author = {Mor Ventura, Eyal Ben-David, Anna Korhonen and Roi Reichart},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2025},
  doi = {10.1162/tacl\_a\_00732},
  url = {https://doi.org/10.1162/tacl_a_00732}
}
```

- [← previous How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark](https://md.research.elamur.ai/free/en/papers/yang-2025-llm-reasoning-distracted-irrelevant-context/)
- [next → PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning](https://md.research.elamur.ai/free/en/papers/zhang-2025-physreason-comprehensive-benchmark-physics-based/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/)

## References

37 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abubakar Abid, Maheen Farooqi, and James Zou. 2021. Large language models associate muslims with violence. Nature Machine Intelligence, 3(6):461–463. https://doi.org/10.1038/s42256-021-00359-2 — [doi:10.1038/s42256-021-00359-2](https://doi.org/10.1038/s42256-021-00359-2) [↗](https://doi.org/10.1038/s42256-021-00359-2)
2. Hila Chefer, Oran Lang, Mor Geva, Volodymyr Polosukhin, Assaf Shocher, Michal Irani, Inbar Likely referring to George Orwell, the author of the book 1984. [find](https://scholar.google.com/scholar?q=Hila+Chefer%2C+Oran+Lang%2C+Mor+Geva%2C+Volodymyr+Polosukhin%2C+Assaf+Shocher%2C+Michal+Irani%2C+Inbar+Likely+referring+to+George+Orwell%2C+the+author+of+the+book+1984%2E)
3. Mosseri, and Lior Wolf. 2023. The hidden language of diffusion models. arXiv preprint arXiv:2306.00966. — [arXiv:2306.00966](https://arxiv.org/abs/2306.00966) [find](https://scholar.google.com/scholar?q=Mosseri%2C+and+Lior+Wolf%2E+2023%2E+The+hidden+language+of+diffusion+models%2E+arXiv+preprint+arXiv%3A2306%2E00966%2E+%E2%80%94+%5BarXiv%3A2306%2E00966%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2306%2E00966%29)
4. Nithish Kannen, Arif Ahmad, Marco Andreetto, Vinodkumar Prabhakaran, Utsav Prabhu, Adji B. Dieng, Pushpak Bhattacharyya, and Shachi Dave. 2024. Beyond aesthetics: Cultural competence in text-to-image models. [find](https://scholar.google.com/scholar?q=Nithish+Kannen%2C+Arif+Ahmad%2C+Marco+Andreetto%2C+Vinodkumar+Prabhakaran%2C+Utsav+Prabhu%2C+Adji+B%2E+Dieng%2C+Pushpak+Bhattacharyya%2C+and+Shachi+Dave%2E+2024%2E+Beyond+aesthetics%3A+Cultural+competence+in+text%2Dto%2Dimage+)
5. Mehdi Cherti, Romain Beaumont, Ross Wightman, Mitchell Wortsman, Gabriel Ilharco, Cade Gordon, Christoph Schuhmann, Ludwig Schmidt, and Jenia Jitsev. 2022. [Reproducible scaling laws for contrastive language-image learning](https://md.research.elamur.ai/free/en/papers/cherti-2022-reproducible-scaling-laws-contrastive-language/). https://doi.org/10.1109/CVPR52729.2023.00276 [↗](https://doi.org/10.1109/CVPR52729.2023.00276)
6. Hyung-Kwon Ko, Gwanmo Park, Hyeon Jeon, Jaemin Jo, Juho Kim, and Jinwook Seo. 2023. Large-scale text-to-image generation models for visual artists’ creative works. In Proceedings of the 28th International Conference on Intelligent User Interfaces, pages 919–933. https://doi.org/10.1145/3581641 .3584… — [doi:10.1145/3581641](https://doi.org/10.1145/3581641) [↗](https://doi.org/10.1145/3581641)
7. Jaemin Cho, Abhay Zala, and Mohit Bansal. 2022. Dall-eval: Probing the reasoning skills and social biases of text-to-image generative models. arXiv preprint arXiv:2202.04053. https://doi.org/10.1109/ICCV51070 .2023.00283 [↗](https://doi.org/10.1109/ICCV51070)
8. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. [Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models](https://md.research.elamur.ai/free/en/papers/li-2023-blip-2-bootstrapping-language-image/). arXiv preprint arXiv:2301.12597.
9. DeepFloyd. 2023. deepfloyd.ai. [find](https://scholar.google.com/scholar?q=DeepFloyd%2E+2023%2E+deepfloyd%2Eai%2E)
10. Jacob Devlin. 2018. mbert. — [Larger-Scale Transformers for Multilingual Masked Language Modeling](https://md.research.elamur.ai/free/en/papers/goyal-2021-larger-scale-transformers-multilingual-masked/) [https://github.com/google-research/bert/blob/master/multilingual.md](https://github.com/google-research/bert/blob/master/multilingual.md) Naman Goyal, Jingfei Du, Myle Ott, Giri Anantharaman, and Alexis Conneau. 2021. Larger-scale transformers for multilingual masked language modeling. arXiv preprint arXiv:2105.00572. https://doi.org/10 .1… [↗](https://github.com/google-research/bert/blob/master/multilingual.md)
11. Bingshuai Liu, Longyue Wang, Chenyang Lyu, Yong Zhang, Jinsong Su, Shuming Shi, and Zhaopeng Tu. 2023. On the cultural gap in text-to-image generation. arXiv preprint arXiv: 2307.02971. — [arXiv:2307.02971](https://arxiv.org/abs/2307.02971) [find](https://scholar.google.com/scholar?q=Bingshuai+Liu%2C+Longyue+Wang%2C+Chenyang+Lyu%2C+Yong+Zhang%2C+Jinsong+Su%2C+Shuming+Shi%2C+and+Zhaopeng+Tu%2E+2023%2E+On+the+cultural+gap+in+text%2Dto%2Dimage+generation%2E+arXiv+preprint+arXiv%3A+2307%2E02971%2E+%E2%80%94+%5BarXiv%3A2307%2E)
12. Fangyu Liu, Emanuele Bugliarello, Edoardo Maria Ponti, Siva Reddy, Nigel Collier, and Desmond Elliott. 2021. Visually grounded reasoning across languages and cultures. arXiv preprint arXiv:2109.13238. https://doi.org/10.1556/084.2021.00009 [↗](https://doi.org/10.1556/084.2021.00009)
13. Christian Haerpfer, Ronald Inglehart, Alejandro Moreno, Christian Welzel, Kseniya Kizilova, Jaime Diez-Medrano, Marta Lagos, Pippa Norris, Eduard Ponarin, and Bi Puranen. 2022. World values survey wave 7 (2017–2022) cross-national data-set. World Values Survey Association. [find](https://scholar.google.com/scholar?q=Christian+Haerpfer%2C+Ronald+Inglehart%2C+Alejandro+Moreno%2C+Christian+Welzel%2C+Kseniya+Kizilova%2C+Jaime+Diez%2DMedrano%2C+Marta+Lagos%2C+Pippa+Norris%2C+Eduard+Ponarin%2C+and+Bi+Puranen%2E+2022%2E+World+values+survey+wav)
14. Adyasha Maharana, Darryl Hannan, and Mohit Bansal. 2022. Storydall-e: Adapting pretrained text-to-image transformers for story continuation. In European Conference on Computer Vision, pages 70–87. Springer. https://doi.org/10.1007/978-3-031-19836-6 5 [↗](https://doi.org/10.1007/978-3-031-19836-6)
15. Reem I. Masoud, Ziquan Liu, Martin Ferianc, Philip Treleaven, and Miguel Rodrigues. 2023. [Cultural alignment in large language models: An explanatory analysis based on hofstede’s cultural dimensions](https://md.research.elamur.ai/free/en/papers/masoud-2025-cultural-alignment-large-language-models/).
16. G. Hofstede, G. J. Hofstede, and M. Minkov 2010. Cultures and Organizations: Software of the Mind (3rd ed.). McGraw-Hill Professional. [find](https://scholar.google.com/scholar?q=G%2E+Hofstede%2C+G%2E+J%2E+Hofstede%2C+and+M%2E+Minkov+2010%2E+Cultures+and+Organizations%3A+Software+of+the+Mind+%283rd+ed%2E%29%2E+McGraw%2DHill+Professional%2E)
17. Geert Hofstede. 1983. Dimensions of national cultures in fifty countries and three regions. In J. B. Deregowski, S. Dziurawiec, and R. C. Annis (Eds.), Expiscations in Cross-Cultural Psychology, pages 335–355. [find](https://scholar.google.com/scholar?q=Geert+Hofstede%2E+1983%2E+Dimensions+of+national+cultures+in+fifty+countries+and+three+regions%2E+In+J%2E+B%2E+Deregowski%2C+S%2E+Dziurawiec%2C+and+R%2E+C%2E+Annis+%28Eds%2E%29%2C+Expiscations+in+Cross%2DCultural+Psychology%2C+pages)
18. Robert R. McCrae and Jüri Allik. 2002. The Five-factor Model of Personality Across Cultures. Springer Science & Business Media. https://doi.org/10.1007/978-1-4615 -0763-5 — [doi:10.1007/978-1-4615](https://doi.org/10.1007/978-1-4615) [↗](https://doi.org/10.1007/978-1-4615)
19. Akshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo, Shachi Dave, Rida Qadri, Chandan K. Reddy, and Sunipa Dev. 2024. Visage: A global-scale analysis of visual stereotypes in text-to-image generation. [find](https://scholar.google.com/scholar?q=Akshita+Jha%2C+Vinodkumar+Prabhakaran%2C+Remi+Denton%2C+Sarah+Laszlo%2C+Shachi+Dave%2C+Rida+Qadri%2C+Chandan+K%2E+Reddy%2C+and+Sunipa+Dev%2E+2024%2E+Visage%3A+A+global%2Dscale+analysis+of+visual+stereotypes+in+text%2Dto%2Dimage+)
20. Ranjita Naik and Besmira Nushi. 2023. Social biases through the text-to-image generation lens. arXiv preprint arXiv:2304.06034. https://doi.org/10.1145/3600211.3604711 — [doi:10.1145/3600211.3604711](https://doi.org/10.1145/3600211.3604711) [↗](https://doi.org/10.1145/3600211.3604711)
21. Tarek Naous, Michael J. Ryan, and Wei Xu. 2023. [Having beer after prayer? Measuring cultural bias in large language models](https://md.research.elamur.ai/free/en/papers/naous-2023-having-beer-after-prayer-measuring/). arXiv preprint arXiv:2305.14456. https://doi.org/10 .18653/v1/2024.acl-long.862 latent diffusion models. https://doi.org/10.1109/CVPR52688.2022.01042
22. Michael Saxon and William Yang Wang. 2023. Multilingual conceptual coverage in text-to-image models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4831–4848, Toronto, Canada. Association for Computational Linguistics. https:… [find](https://scholar.google.com/scholar?q=Michael+Saxon+and+William+Yang+Wang%2E+2023%2E+Multilingual+conceptual+coverage+in+text%2Dto%2Dimage+models%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+)
23. Vinodkumar Prabhakaran, Rida Qadri, and Ben Hutchinson. 2022. Cultural incongruencies in artificial intelligence. CoRR, abs/2211.13069. — [arXiv:2211.13069](https://arxiv.org/abs/2211.13069) [find](https://scholar.google.com/scholar?q=Vinodkumar+Prabhakaran%2C+Rida+Qadri%2C+and+Ben+Hutchinson%2E+2022%2E+Cultural+incongruencies+in+artificial+intelligence%2E+CoRR%2C+abs%2F2211%2E13069%2E+%E2%80%94+%5BarXiv%3A2211%2E13069%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2211%2E13069%29)
24. Rifki Afina Putri, Faiz Ghifari Haznitrama, Dea Adhista, and Alice Oh. 2024. [Can llm generate culturally relevant commonsense QA data? Case study in indonesian and sundanese](https://md.research.elamur.ai/free/en/papers/putri-2024-can-llm-generate-culturally-relevant/). ArXiv, abs/2402.17302.
25. Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, et al. 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv: 2211.05100. [find](https://scholar.google.com/scholar?q=Teven+Le+Scao%2C+Angela+Fan%2C+Christopher+Akiki%2C+Ellie+Pavlick%2C+Suzana+Ilic%CC%81%2C+Daniel+Hesslow%2C+Roman+Castagne%CC%81%2C+Alexandra+Sasha+Luccioni%2C+Franc%CC%A7ois+Yvon%2C+Matthias+Galle%CC%81%2C+et+al%2E+2022%2E+Bloom%3A+A+176b%2Dparame)
26. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International Conference on Machin…
27. Shalom H. Schwartz. 1994. Beyond individualism/collectivism: New cultural dimensions of values. SAGE Publications, Inc. [find](https://scholar.google.com/scholar?q=Shalom+H%2E+Schwartz%2E+1994%2E+Beyond+individualism%2Fcollectivism%3A+New+cultural+dimensions+of+values%2E+SAGE+Publications%2C+Inc%2E)
28. Eric Michael Smith, Melissa Hall, Melanie Kambadur, Eleonora Presani, and Adina Williams. 2022. [‘‘I’m sorry to hear that’’: Finding new biases in language models with a holistic descriptor dataset](https://md.research.elamur.ai/free/en/papers/smith-2022-i-m-sorry-hear-that/). In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9180–…
29. Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. [Hierarchical text-conditional image generation with clip latents](https://md.research.elamur.ai/free/en/papers/ramesh-2022-hierarchical-text-conditional-image-generation/). arXiv preprint arXiv:2204.06125.
30. Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. [Zero-shot text-to-image generation](https://md.research.elamur.ai/free/en/papers/ramesh-2021-zero-shot-text-image-generation/). In International Conference on Machine Learning, pages 8821–8831. PMLR.
31. Aida Ramezani and Yang Xu. 2023. [Knowledge of cultural moral norms in large language models](https://md.research.elamur.ai/free/en/papers/ramezani-2023-knowledge-cultural-moral-norms-large/). arXiv preprint arXiv:2306.01857. https://doi.org/10.18653/v1/2023 .acl-long.26 [↗](https://doi.org/10.18653/v1/2023)
32. Abhinav Rao, Akhila Yerukola, Vishwa Shah, Katharina Reinecke, and Maarten Sap. 2024. Normad: A benchmark for measuring the cultural adaptability of large language models. ArXiv, abs/2404.12464. — [arXiv:2404.12464](https://arxiv.org/abs/2404.12464) [find](https://scholar.google.com/scholar?q=Abhinav+Rao%2C+Akhila+Yerukola%2C+Vishwa+Shah%2C+Katharina+Reinecke%2C+and+Maarten+Sap%2E+2024%2E+Normad%3A+A+benchmark+for+measuring+the+cultural+adaptability+of+large+language+models%2E+ArXiv%2C+abs%2F2404%2E12464%2E+%E2%80%94+%5Bar)
33. Lukas Struppek, Dominik Hintersdorf, and Kristian Kersting. 2022. The biased artist: Exploiting cultural biases via homoglyphs in text-guided image generation models. arXiv preprint arXiv:2209.08891. https://doi.org/10.1613/jair.1.15388 — [doi:10.1613/jair.1.15388](https://doi.org/10.1613/jair.1.15388) [↗](https://doi.org/10.1613/jair.1.15388)
34. Maxim Tkachenko, Mikhail Malyuk, Andrey Holmanyuk, and Nikolai Liubimov. 2020–2022. Label Studio: Data labeling software. Open source software available from [https://github.com/heartexlabs/label](https://github.com/heartexlabs/label) -studio. [↗](https://github.com/heartexlabs/label)
35. Samia Touileb, Lilja Øvrelid, and Erik Velldal. 2022. Occupational biases in Norwegian and multilingual language models. In Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 200–211. https://doi.org/10.18653/v1/2022.gebnlp-1.21 [↗](https://doi.org/10.18653/v1/2022.gebnlp-1.21)
36. Milton Rokeach. 1967. Rokeach value survey. The Nature of Human Values. [find](https://scholar.google.com/scholar?q=Milton+Rokeach%2E+1967%2E+Rokeach+value+survey%2E+The+Nature+of+Human+Values%2E)
37. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2021. High-resolution image synthesis with [find](https://scholar.google.com/scholar?q=Robin+Rombach%2C+Andreas+Blattmann%2C+Dominik+Lorenz%2C+Patrick+Esser%2C+and+Bjo%CC%88rn+Ommer%2E+2021%2E+High%2Dresolution+image+synthesis+with)

*Updated 30 October 2026*