{"id":"https://openalex.org/W4396945138","doi":"https://doi.org/10.48550/arxiv.2405.08748","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","display_name":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","publication_year":2024,"publication_date":"2024-05-14","ids":{"openalex":"https://openalex.org/W4396945138","doi":"https://doi.org/10.48550/arxiv.2405.08748"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.08748","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.08748","pdf_url":"https://arxiv.org/pdf/2405.08748","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.08748","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100446638","display_name":"Zhimin Li","orcid":"https://orcid.org/0000-0003-0972-952X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Zhimin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326960","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-1075-9745"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jianwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102310454","display_name":"Qin Lin","orcid":"https://orcid.org/0009-0008-3462-9735"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Qin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083206979","display_name":"Jiangfeng Xiong","orcid":"https://orcid.org/0000-0001-6840-8262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Jiangfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018425393","display_name":"Yanxin Long","orcid":"https://orcid.org/0000-0001-8784-8343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Yanxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101354548","display_name":"Xinchi Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Xinchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010475326","display_name":"Yingfang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yingfang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024864770","display_name":"Xingchao Liu","orcid":"https://orcid.org/0009-0005-5592-5128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xingchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052117191","display_name":"Minbin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Minbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110321909","display_name":"Zedong Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Zedong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070471298","display_name":"Dayou Chen","orcid":"https://orcid.org/0000-0001-8616-2657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Dayou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100601608","display_name":"Jiajun He","orcid":"https://orcid.org/0009-0003-8236-8422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Jiajun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066324471","display_name":"Jiahao Li","orcid":"https://orcid.org/0009-0001-5933-7367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiahao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104196287","display_name":"Wenyue Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wenyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374074","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0001-9049-091X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032451167","display_name":"Rongwei Quan","orcid":"https://orcid.org/0000-0002-1221-4140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan, Rongwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042325439","display_name":"Jianxiang Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Jianxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144994","display_name":"Jiabin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiabin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101166847","display_name":"Xiaoyan Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Xiaoyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102880860","display_name":"Xiaoxiao Zheng","orcid":"https://orcid.org/0000-0002-5275-1143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Xiaoxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108147206","display_name":"Yixuan Li","orcid":"https://orcid.org/0000-0001-7653-2378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030062634","display_name":"Jihong Zhang","orcid":"https://orcid.org/0000-0003-3854-8891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jihong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357847","display_name":"Meng Chen","orcid":"https://orcid.org/0000-0001-7319-8570"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101311782","display_name":"Jie Liu","orcid":"https://orcid.org/0009-0007-6592-0384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102216318","display_name":"Zheng Fang","orcid":"https://orcid.org/0009-0000-3537-2654"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013332473","display_name":"Weiyan Wang","orcid":"https://orcid.org/0000-0002-4105-0691"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Weiyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025328651","display_name":"Jinbao Xue","orcid":"https://orcid.org/0009-0003-4087-9873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Jinbao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077922409","display_name":"Yangyu Tao","orcid":"https://orcid.org/0009-0003-0536-4321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Yangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059894156","display_name":"Jianchen Zhu","orcid":"https://orcid.org/0000-0002-5988-3704"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jianchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079462894","display_name":"Kai Liu","orcid":"https://orcid.org/0000-0002-3124-8514"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101354547","display_name":"Sihuan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Sihuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111197074","display_name":"Yifu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yifu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101031495","display_name":"Yun Li","orcid":"https://orcid.org/0000-0002-5982-9265"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048777284","display_name":"Dongdong Wang","orcid":"https://orcid.org/0000-0001-8452-0158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Dongdong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101869083","display_name":"Mingtao Chen","orcid":"https://orcid.org/0000-0001-7316-387X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Mingtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021626498","display_name":"Zhichao Hu","orcid":"https://orcid.org/0000-0003-1628-4274"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zhichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451726","display_name":"Xiao Xiao","orcid":"https://orcid.org/0000-0002-4292-9657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112958264","display_name":"Yan Chen","orcid":"https://orcid.org/0000-0001-9206-587X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005799407","display_name":"Yuhong Liu","orcid":"https://orcid.org/0000-0002-2565-8701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114207477","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0001-9873-304X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401406","display_name":"Di Wang","orcid":"https://orcid.org/0000-0002-0832-2368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602227","display_name":"Yong Yang","orcid":"https://orcid.org/0000-0002-4241-9972"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041948410","display_name":"Jie Jiang","orcid":"https://orcid.org/0000-0002-9634-4152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5104261307","display_name":"Qinglin Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Qinglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":45,"corresponding_author_ids":["https://openalex.org/A5100446638"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11222","display_name":"Magnetic Properties and Applications","score":0.9025999903678894,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11222","display_name":"Magnetic Properties and Applications","score":0.9025999903678894,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5087862610816956},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4212518632411957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41218653321266174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18224367499351501},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10417824983596802},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08429273962974548},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05599278211593628}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5087862610816956},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4212518632411957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41218653321266174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18224367499351501},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10417824983596802},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08429273962974548},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05599278211593628}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2405.08748","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.08748","pdf_url":"https://arxiv.org/pdf/2405.08748","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2405.08748","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.08748","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.08748","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.08748","pdf_url":"https://arxiv.org/pdf/2405.08748","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"We":[0,29],"present":[1],"Hunyuan-DiT,":[2,17],"a":[3,34,53,97],"text-to-image":[4],"diffusion":[5],"transformer":[6,22],"with":[7,72,88,104],"fine-grained":[8,48],"understanding":[9],"of":[10,62],"both":[11],"English":[12],"and":[13,26,40,75,109],"Chinese.":[14],"To":[15],"construct":[16],"we":[18,51],"carefully":[19],"design":[20],"the":[21,60,63,80],"structure,":[23],"text":[24],"encoder,":[25],"positional":[27],"encoding.":[28],"also":[30],"build":[31],"from":[32],"scratch":[33],"whole":[35],"data":[36,42],"pipeline":[37],"to":[38,58,79],"update":[39],"evaluate":[41],"for":[43],"iterative":[44],"model":[45],"optimization.":[46],"For":[47],"language":[49],"understanding,":[50],"train":[52],"Multimodal":[54],"Large":[55],"Language":[56],"Model":[57],"refine":[59],"captions":[61],"images.":[64],"Finally,":[65],"Hunyuan-DiT":[66,95],"can":[67],"perform":[68],"multi-turn":[69],"multimodal":[70],"dialogue":[71],"users,":[73],"generating":[74],"refining":[76],"images":[77],"according":[78],"context.":[81],"Through":[82],"our":[83],"holistic":[84],"human":[85,93],"evaluation":[86],"protocol":[87],"more":[89],"than":[90],"50":[91],"professional":[92],"evaluators,":[94],"sets":[96],"new":[98],"state-of-the-art":[99],"in":[100],"Chinese-to-image":[101],"generation":[102],"compared":[103],"other":[105],"open-source":[106],"models.":[107],"Code":[108],"pretrained":[110],"models":[111],"are":[112],"publicly":[113],"available":[114],"at":[115],"github.com/Tencent/HunyuanDiT":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2024-05-16T00:00:00"}
