{"id":"https://openalex.org/W4409486164","doi":"https://doi.org/10.1145/3730403","title":"StyleInject: Parameter Efficient Tuning of Text-to-Image Diffusion Models","display_name":"StyleInject: Parameter Efficient Tuning of Text-to-Image Diffusion Models","publication_year":2025,"publication_date":"2025-04-16","ids":{"openalex":"https://openalex.org/W4409486164","doi":"https://doi.org/10.1145/3730403"},"language":"en","primary_location":{"id":"doi:10.1145/3730403","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3730403","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006824435","display_name":"Mohan Zhou","orcid":"https://orcid.org/0000-0003-3250-4978"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mohan Zhou","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054533256","display_name":"Yalong Bai","orcid":"https://orcid.org/0000-0002-8416-9027"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yalong Bai","raw_affiliation_strings":["Du Xiaoman Technology, Beijing, China","Du Xiaoman, China"],"affiliations":[{"raw_affiliation_string":"Du Xiaoman Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Du Xiaoman, China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101837857","display_name":"Qing Yang","orcid":"https://orcid.org/0009-0005-8596-884X"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Yang","raw_affiliation_strings":["Du Xiaoman Technology, Beijing, China","Du Xiaoman, China"],"affiliations":[{"raw_affiliation_string":"Du Xiaoman Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Du Xiaoman, China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006824435"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.2784,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78723339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"21","issue":"5","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9596999883651733,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8751449584960938},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5521767735481262},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5088203549385071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39806729555130005},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35523781180381775},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32274964451789856},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07416418194770813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8751449584960938},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5521767735481262},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5088203549385071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39806729555130005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35523781180381775},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32274964451789856},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07416418194770813},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3730403","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3730403","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2559655401","https://openalex.org/W2603777577","https://openalex.org/W2962770929","https://openalex.org/W2965373594","https://openalex.org/W2990138404","https://openalex.org/W3153469116","https://openalex.org/W4281485151","https://openalex.org/W4283731241","https://openalex.org/W4303443407","https://openalex.org/W4306820534","https://openalex.org/W4308241978","https://openalex.org/W4312933868","https://openalex.org/W4319316769","https://openalex.org/W4361271773","https://openalex.org/W4366208220","https://openalex.org/W4380994608","https://openalex.org/W4385682474","https://openalex.org/W4386071831","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4390873054","https://openalex.org/W4393260012"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,41,89,123],"fine-tune":[3],"generative":[4,143],"models":[5],"for":[6,29,70],"text-to-image":[7,38,71],"generation":[8],"tasks":[9,39],"is":[10,27],"crucial,":[11],"particularly":[12,131],"when":[13],"facing":[14],"the":[15,42,81,94,101,104,111,114],"complexity":[16],"involved":[17],"in":[18,37,126,133,167],"accurately":[19],"interpreting":[20],"and":[21,56,136,151,172],"visualizing":[22],"textual":[23],"inputs.":[24],"While":[25],"LoRA":[26,166],"efficient":[28],"language":[30],"model":[31,159],"adaptation,":[32],"it":[33],"often":[34],"falls":[35],"short":[36],"due":[40],"intricate":[43],"demands":[44],"of":[45,54,83,96,103,140],"image":[46],"generation,":[47],"such":[48],"as":[49,155,157],"accommodating":[50],"a":[51,65,138],"broad":[52],"spectrum":[53],"styles":[55,91,125],"nuances.":[57],"To":[58],"bridge":[59],"this":[60],"gap,":[61],"we":[62],"introduce":[63],"StyleInject,":[64],"specialized":[66],"fine-tuning":[67,154],"approach":[68,108],"tailored":[69],"models.":[72,144],"StyleInject":[73,129,163],"comprises":[74],"multiple":[75],"parallel":[76],"low-rank":[77],"parameter":[78,180],"matrices,":[79],"maintaining":[80],"diversity":[82],"visual":[84,97],"features.":[85],"It":[86],"dynamically":[87],"adapts":[88],"varying":[90],"by":[92],"adjusting":[93],"variance":[95],"features":[98],"based":[99],"on":[100,113],"characteristics":[102],"input":[105],"signal.":[106],"This":[107],"significantly":[109],"minimizes":[110],"impact":[112],"original":[115],"model\u2019s":[116],"text-image":[117,169],"alignment":[118],"capabilities":[119],"while":[120,177],"adeptly":[121],"adapting":[122],"various":[124],"transfer":[127],"learning.":[128],"proves":[130],"effective":[132],"learning":[134],"from":[135],"enhancing":[137],"range":[139],"advanced,":[141],"community-fine-tuned":[142],"Our":[145],"comprehensive":[146],"experiments,":[147],"including":[148],"both":[149,168],"small-sample":[150],"large-scale":[152],"data":[153],"well":[156],"base":[158],"distillation,":[160],"show":[161],"that":[162],"surpasses":[164],"traditional":[165],"semantic":[170],"consistency":[171],"human":[173],"preference":[174],"evaluation,":[175],"all":[176],"ensuring":[178],"greater":[179],"efficiency.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}