{"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/pea-diffusion-parameter-efficient-adapter","title":"PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation","arxiv_id":"2311.17086","date":"2023-11-28","proceeding":null,"authors":["Jian Ma","Chen Chen","Qingsong Xie","Haonan Lu"],"abstract":"Text-to-image diffusion models are well-known for their ability to generate realistic images based on textual prompts. However, the existing works have predominantly focused on English, lacking support for non-English text-to-image models. The most commonly used translation methods cannot solve the generation problem related to language culture, while training from scratch on a specific language dataset is prohibitively expensive. In this paper, we are inspired to propose a simple plug-and-play language transfer method based on knowledge distillation. All we need to do is train a lightweight MLP-like parameter-efficient adapter (PEA) with only 6M parameters under teacher knowledge distillation along with a small parallel data corpus. We are surprised to find that freezing the parameters of UNet can still achieve remarkable performance on the language-specific prompt evaluation set, demonstrating that PEA can stimulate the potential generation ability of the original UNet. Additionally, it closely approaches the performance of the English text-to-image model on a general prompt evaluation set. Furthermore, our adapter can be used as a plugin to achieve significant results in downstream tasks in cross-lingual text-to-image generation. Code will be available at: https://github.com/OPPO-Mente-Lab/PEA-Diffusion","url_abs":"https://arxiv.org/abs/2311.17086v2","url_pdf":"https://arxiv.org/pdf/2311.17086v2.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":"pea-diffusion-parameter-efficient-adapter","repo_url":"https://github.com/OPPO-Mente-Lab/PEA-Diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-text-to-image-generation","task_name":"Cross-lingual Text-to-Image Generation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.17086","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}