In this work, we explore a cost-effective framework for multilingual image generation. We find that, unlike models tuned on high-quality images with multilingual annotations, leveraging text encoders pre-trained on widely available, noisy Internet image-text pairs significantly enhances data efficiency in text-to-image (T2I) generation across multiple languages.Based on this insight, we introduce MuLan, Multi-Language adapter, a lightweight language adapter with fewer than 20M parameters, trained alongside a frozen text encoder and image diffusion model. Compared to previous multilingual T2I models, this framework offers: (1) Cost efficiency. Using readily accessible English data and off-the-shelf multilingual text encoders minimizes the training cost; (2) High performance. Achieving comparable generation capabilities in over 110 languages with CLIP similarity scores nearly matching those in English (39.57 for English vs. 39.61 for other languages); and (3) Broad applicability. Seamlessly integrating with compatible community tools like LoRA, LCM, ControlNet, and IP-Adapter, expanding its potential use cases.
@article{arxiv.2412.01271,
title = {MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost},
author = {Sen Xing and Muyan Zhong and Zeqiang Lai and Liangchen Li and Jiawen Liu and Yaohui Wang and Jifeng Dai and Wenhai Wang},
journal= {arXiv preprint arXiv:2412.01271},
year = {2025}
}