# CRAFT: Cultural Russian-Oriented Dataset Adaptation for Focused Text-to-Image Generation

arXiv: https://arxiv.org/abs/2505.04851 · HTML: https://mlsanity.com/paper/2505.04851/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 30 of 31)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack](https://mlsanity.com/paper/2309.15807/) (2023)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World](https://mlsanity.com/paper/1711.08536/) (2017)
- [Does Object Recognition Work for Everyone?](https://mlsanity.com/paper/1906.02659/) (2019)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion](https://mlsanity.com/paper/2310.03502/) (2023)
- [A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning](https://mlsanity.com/paper/2203.11933/) (2022)
- [COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances](https://mlsanity.com/paper/2311.01012/) (2023)
- [Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis](https://mlsanity.com/paper/2209.08891/) (2022)
- [Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework](https://mlsanity.com/paper/2410.21061/) (2024)
- [The Dark Side of Dataset Scaling: Evaluating Racial Classification in Multimodal Models](https://mlsanity.com/paper/2405.04623/) (2024)
- [Cross-Cultural Transfer Learning for Chinese Offensive Language Detection](https://mlsanity.com/paper/2303.17927/) (2023)
- [Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features](https://mlsanity.com/paper/2310.06458/) (2023)
- [Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys](https://mlsanity.com/paper/2401.10352/) (2024)
- [From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models](https://mlsanity.com/paper/2407.00263/) (2024)
- [Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection](https://mlsanity.com/paper/2303.02513/) (2023)
- [Situating the social issues of image generation models in the model life cycle: a sociotechnical approach](https://mlsanity.com/paper/2311.18345/) (2023)
- [FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline](https://mlsanity.com/paper/2311.13073/) (2023)
- [Cultural Adaptation of Recipes](https://mlsanity.com/paper/2310.17353/) (2023)
- [Pinpointing Why Object Recognition Performance Degrades Across Income Levels and Geographies](https://mlsanity.com/paper/2304.05391/) (2023)

## Abstract (arXiv)

Despite the fact that popular text-to-image generation models cope well with international and general cultural queries, they have a significant knowledge gap regarding individual cultures. This is due to the content of existing large training datasets collected on the Internet, which are predominantly based on Western European or American popular culture. Meanwhile, the lack of cultural adaptation of the model can lead to incorrect results, a decrease in the generation quality, and the spread of stereotypes and offensive content. In an effort to address this issue, we examine the concept of cultural code and recognize the critical importance of its understanding by modern image generation models, an issue that has not been sufficiently addressed in the research community to date. We propose the methodology for collecting and processing the data necessary to form a dataset based on the cultural code, in particular the Russian one. We explore how the collected data affects the quality of generations in the national domain and analyze the effectiveness of our approach using the Kandinsky 3.1 text-to-image model. Human evaluation results demonstrate an increase in the level of awareness of Russian culture in the model.