# Text to Image Generation: Leaving no Language Behind

arXiv: https://arxiv.org/abs/2208.09333 · HTML: https://mlsanity.com/paper/2208.09333/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 19 Aug 2022.

## Builds on (most cited first, 11 of 11)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [When Will AI Exceed Human Performance? Evidence from AI Experts](https://mlsanity.com/paper/1705.08807/) (2017)
- [Learning to Scale Multilingual Representations for Vision-Language Tasks](https://mlsanity.com/paper/2004.04312/) (2020)

## Built on by (most cited first, 4 of 4)

- [Towards Equitable Representation in Text-to-Image Synthesis Models with the Cross-Cultural Understanding Benchmark (CCUB) Dataset](https://mlsanity.com/paper/2301.12073/) (2023)
- [Playing with words: Comparing the vocabulary and lexical diversity of ChatGPT and humans](https://mlsanity.com/paper/2308.07462/) (2023)
- [A Comparative Investigation of Compositional Syntax and Semantics in DALL-E 2](https://mlsanity.com/paper/2403.12294/) (2024)
- [Open Conversational LLMs do not know most Spanish words](https://mlsanity.com/paper/2403.15491/) (2024)

## Abstract (arXiv)

One of the latest applications of Artificial Intelligence (AI) is to generate images from natural language descriptions. These generators are now becoming available and achieve impressive results that have been used for example in the front cover of magazines. As the input to the generators is in the form of a natural language text, a question that arises immediately is how these models behave when the input is written in different languages. In this paper we perform an initial exploration of how the performance of three popular text-to-image generators depends on the language. The results show that there is a significant performance degradation when using languages other than English, especially for languages that are not widely used. This observation leads us to discuss different alternatives on how text-to-image generators can be improved so that performance is consistent across different languages. This is fundamental to ensure that this new technology can be used by non-native English speakers and to preserve linguistic diversity.