{"id":"https://openalex.org/W4403791567","doi":"https://doi.org/10.1145/3664647.3680848","title":"PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering","display_name":"PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791567","doi":"https://doi.org/10.1145/3664647.3680848"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680848","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680848","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3680848?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3680848?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059455992","display_name":"Y. N. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yibin Wang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693727","display_name":"Weizhong Zhang","orcid":"https://orcid.org/0000-0001-7311-0698"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhong Zhang","raw_affiliation_strings":["School of Data Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Data Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026233608","display_name":"Jianwei Zheng","orcid":"https://orcid.org/0000-0001-6017-0552"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Zheng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100625873","display_name":"Cheng Jin","orcid":"https://orcid.org/0000-0003-3063-1957"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Jin","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059455992"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.2231,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81088175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10824","last_page":"10832"},"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":0.9997000098228455,"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":0.9997000098228455,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9987999796867371,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.564970850944519},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.5540541410446167},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45438089966773987},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4513496458530426},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4419834613800049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3575797975063324},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12185338139533997},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.0874895453453064},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.07378208637237549}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.564970850944519},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.5540541410446167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45438089966773987},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4513496458530426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4419834613800049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3575797975063324},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12185338139533997},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0874895453453064},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.07378208637237549},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680848","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680848","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3680848?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-161554","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-161554","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3664647.3680848","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680848","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3680848?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7911025937","display_name":null,"funder_award_id":"22dz1204900","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403791567.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2938671123","https://openalex.org/W2939873304","https://openalex.org/W2960974111","https://openalex.org/W2962785568","https://openalex.org/W2963271314","https://openalex.org/W2982014123","https://openalex.org/W2982695696","https://openalex.org/W3008540959","https://openalex.org/W3009134234","https://openalex.org/W3028869078","https://openalex.org/W3034365683","https://openalex.org/W3036167779","https://openalex.org/W3110387477","https://openalex.org/W3120238727","https://openalex.org/W3154831990","https://openalex.org/W3216352822","https://openalex.org/W4231697575","https://openalex.org/W4312824283","https://openalex.org/W4312933868","https://openalex.org/W4312966374","https://openalex.org/W4320087030","https://openalex.org/W4385270985","https://openalex.org/W4385271281","https://openalex.org/W4386076425","https://openalex.org/W4386083141","https://openalex.org/W4386160292","https://openalex.org/W4390872636","https://openalex.org/W4393148711","https://openalex.org/W4393153708","https://openalex.org/W4402727163","https://openalex.org/W4402727823","https://openalex.org/W6779823529"],"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":{"Image":[0],"composition":[1,92],"involves":[2],"seamlessly":[3],"integrating":[4],"given":[5],"objects":[6],"into":[7,185,193],"a":[8,94,128,208],"specific":[9,216],"visual":[10],"context.":[11],"Current":[12],"training-free":[13,130],"methods":[14,78],"rely":[15],"on":[16,54,101],"composing":[17],"attention":[18,138,187],"weights":[19,30],"from":[20,33],"several":[21],"samplers":[22],"to":[23,39,116,200,211,219],"guide":[24,201],"the":[25,83,107,113,122,134,163,169,186,194,198,202,213,223,228,234,237,243],"generator.":[26],"However,":[27],"since":[28],"these":[29,77,161],"are":[31,190],"derived":[32],"disparate":[34],"contexts,":[35],"their":[36,51,67],"combination":[37],"leads":[38],"coherence":[40,235],"confusion":[41],"and":[42,172,177,247,255],"loss":[43],"of":[44,197,215],"appearance":[45],"information.":[46],"These":[47],"issues":[48],"worsen":[49],"with":[50,112,167],"excessive":[52],"focus":[53],"background":[55,115],"generation,":[56],"even":[57],"when":[58],"unnecessary":[59],"in":[60,82,227,236],"this":[61,87],"task.":[62],"This":[63,144,180],"not":[64],"only":[65],"impedes":[66],"swift":[68],"implementation":[69],"but":[70],"also":[71],"compromises":[72],"foreground":[73,102,109],"generation":[74],"quality.":[75],"Moreover,":[76],"introduce":[79,207],"unwanted":[80,224],"artifacts":[81,225],"transition":[84,238],"area.":[85,239],"In":[86],"paper,":[88],"we":[89,125,206],"formulate":[90],"image":[91],"as":[93],"subject-based":[95],"local":[96],"editing":[97],"task,":[98],"solely":[99],"focusing":[100],"generation.":[103],"At":[104],"each":[105,158],"step,":[106],"edited":[108],"is":[110,146,183,259],"combined":[111],"noisy":[114],"maintain":[117],"scene":[118],"consistency.":[119],"To":[120],"address":[121],"remaining":[123],"issues,":[124],"propose":[126],"PrimeComposer,":[127],"faster":[129],"diffuser":[131],"that":[132],"composites":[133],"images":[135],"by":[136,149],"well-designed":[137],"steering":[139,145],"across":[140],"different":[141],"noise":[142],"levels.":[143],"predominantly":[147],"achieved":[148],"our":[150,251],"Correlation":[151],"Diffuser,":[152],"utilizing":[153],"its":[154],"self-attention":[155,195],"layers":[156,196],"at":[157,261],"step.":[159],"Within":[160],"layers,":[162],"synthesized":[164],"subject":[165],"interacts":[166],"both":[168,253],"referenced":[170],"object":[171],"background,":[173],"capturing":[174],"intricate":[175],"details":[176],"coherent":[178],"relationships.":[179],"prior":[181,229],"information":[182],"encoded":[184],"weights,":[188],"which":[189],"then":[191],"integrated":[192],"generator":[199],"synthesis":[203],"process.":[204],"Besides,":[205],"Region-constrained":[209],"Cross-Attention":[210],"confine":[212],"impact":[214],"subject-related":[217],"tokens":[218],"desired":[220],"regions,":[221],"addressing":[222],"shown":[226],"method":[230,241],"thereby":[231],"further":[232],"improving":[233],"Our":[240],"exhibits":[242],"fastest":[244],"inference":[245],"efficiency":[246],"extensive":[248],"experiments":[249],"demonstrate":[250],"superiority":[252],"qualitatively":[254],"quantitatively.":[256],"The":[257],"code":[258],"available":[260],"https://github.com/CodeGoat24/PrimeComposer.":[262]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}