{"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/prompt-refinement-with-image-pivot-for-text","title":"Prompt Refinement with Image Pivot for Text-to-Image Generation","arxiv_id":"2407.00247","date":"2024-06-28","proceeding":null,"authors":["Jingtao Zhan","Qingyao Ai","Yiqun Liu","Yingwei Pan","Ting Yao","Jiaxin Mao","Shaoping Ma","Tao Mei"],"abstract":"For text-to-image generation, automatically refining user-provided natural language prompts into the keyword-enriched prompts favored by systems is essential for the user experience. Such a prompt refinement process is analogous to translating the prompt from \"user languages\" into \"system languages\". However, the scarcity of such parallel corpora makes it difficult to train a prompt refinement model. Inspired by zero-shot machine translation techniques, we introduce Prompt Refinement with Image Pivot (PRIP). PRIP innovatively uses the latent representation of a user-preferred image as an intermediary \"pivot\" between the user and system languages. It decomposes the refinement process into two data-rich tasks: inferring representations of user-preferred images from user languages and subsequently translating image representations into system languages. Thus, it can leverage abundant data for training. Extensive experiments show that PRIP substantially outperforms a wide range of baselines and effectively transfers to unseen systems in a zero-shot manner.","url_abs":"https://arxiv.org/abs/2407.00247v1","url_pdf":"https://arxiv.org/pdf/2407.00247v1.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":"prompt-refinement-with-image-pivot-for-text","repo_url":"https://github.com/jingtaozhan/promptreformulate","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"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"},{"task_slug":"zero-shot-machine-translation","task_name":"Zero-Shot Machine Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.00247","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}