{"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/janus-pro-unified-multimodal-understanding","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","arxiv_id":"2501.17811","date":"2025-01-29","proceeding":null,"authors":["Xiaokang Chen","Zhiyu Wu","Xingchao Liu","Zizheng Pan","Wen Liu","Zhenda Xie","Xingkai Yu","Chong Ruan"],"abstract":"In this work, we introduce Janus-Pro, an advanced version of the previous work Janus. Specifically, Janus-Pro incorporates (1) an optimized training strategy, (2) expanded training data, and (3) scaling to larger model size. With these improvements, Janus-Pro achieves significant advancements in both multimodal understanding and text-to-image instruction-following capabilities, while also enhancing the stability of text-to-image generation. We hope this work will inspire further exploration in the field. Code and models are publicly available.","url_abs":"https://arxiv.org/abs/2501.17811v1","url_pdf":"https://arxiv.org/pdf/2501.17811v1.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":"janus-pro-unified-multimodal-understanding","repo_url":"https://github.com/deepseek-ai/janus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"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":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/on-wise","task":"","dataset":"WISE","model":"Janus-Pro-7B","rank_in_archive_order":10,"of":11,"metrics":{"Biology":"0.36","Chemistry":"0.26","Cultural":"0.30","Overall":"0.35","Physics":"0.42","Space":"0.49","Time":"0.37"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-wise","task":"Image Generation","dataset":"WISE","model":"Janus-pro","rank_in_archive_order":12,"of":14,"metrics":{"Biology":"0.36","Chemistry":"0.26","Cultural":"0.30","Overall":"0.35","Physics":"0.42","Space":"0.49","Time":"0.37"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-wise","task":"Image Generation","dataset":"WISE","model":"Janus","rank_in_archive_order":14,"of":14,"metrics":{"Biology":"0.28","Chemistry":"0.14","Cultural":"0.16","Overall":"0.23","Physics":"0.30","Space":"0.35","Time":"0.26"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-geneval","task":"Text-to-Image Generation","dataset":"GenEval","model":"Janus-Pro-7B","rank_in_archive_order":6,"of":20,"metrics":{"Overall":"0.80"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-geneval","task":"Text-to-Image Generation","dataset":"GenEval","model":"Janus-Pro-1B","rank_in_archive_order":10,"of":20,"metrics":{"Overall":"0.73"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Janus-Pro-7B","rank_in_archive_order":65,"of":231,"metrics":{"GPT-4 score":"50.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Janus-Pro-1B","rank_in_archive_order":116,"of":231,"metrics":{"GPT-4 score":"39.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.17811","atlas_url":"https://app.syntology.ai/?focus=2501.17811","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}