{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mulan-adapting-multilingual-diffusion-models","title":"MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost","arxiv_id":"2412.01271","date":"2024-12-02","proceeding":null,"authors":["Sen Xing","Muyan Zhong","Zeqiang Lai","Liangchen Li","Jiawen Liu","Yaohui Wang","Jifeng Dai","Wenhai Wang"],"abstract":"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 (38.61 for English vs. 37.61 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.","url_abs":"https://arxiv.org/abs/2412.01271v1","url_pdf":"https://arxiv.org/pdf/2412.01271v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mulan-adapting-multilingual-diffusion-models","repo_url":"https://github.com/tiankaihang/min-snr-diffusion-training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.01271","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}