{"id":"https://openalex.org/W4400818431","doi":"https://doi.org/10.1145/3658157","title":"Training-Free Consistent Text-to-Image Generation","display_name":"Training-Free Consistent Text-to-Image Generation","publication_year":2024,"publication_date":"2024-07-19","ids":{"openalex":"https://openalex.org/W4400818431","doi":"https://doi.org/10.1145/3658157"},"language":"en","primary_location":{"id":"doi:10.1145/3658157","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658157","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658157","source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3658157","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039215377","display_name":"Yoad Tewel","orcid":"https://orcid.org/0009-0006-8042-0428"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yoad Tewel","raw_affiliation_strings":["NVIDIA Research, Tel Aviv, Israel","Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0009-0006-8042-0428","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Tel Aviv, Israel","institution_ids":[]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036164473","display_name":"Omri Kaduri","orcid":"https://orcid.org/0009-0003-2099-6263"},"institutions":[{"id":"https://openalex.org/I4210101321","display_name":"Israel Ports Development and Assets (Israel)","ror":"https://ror.org/01e8jps31","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210101321"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Omri Kaduri","raw_affiliation_strings":["Independent Scientist, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0009-0003-2099-6263","affiliations":[{"raw_affiliation_string":"Independent Scientist, Tel Aviv, Israel","institution_ids":["https://openalex.org/I4210101321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057080001","display_name":"Rinon Gal","orcid":"https://orcid.org/0000-0003-4875-965X"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Rinon Gal","raw_affiliation_strings":["NVIDIA Research, Tel Aviv, Israel","Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0003-4875-965X","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Tel Aviv, Israel","institution_ids":[]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010210809","display_name":"Yoni Kasten","orcid":"https://orcid.org/0009-0006-9897-0022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoni Kasten","raw_affiliation_strings":["NVIDIA Research, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0009-0006-9897-0022","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Tel Aviv, Israel","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0001-5578-8892","affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045719865","display_name":"Gal Chechik","orcid":"https://orcid.org/0000-0001-9164-5303"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gal Chechik","raw_affiliation_strings":["NVIDIA Research, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0001-9164-5303","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Tel Aviv, Israel","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080909499","display_name":"Yuval Atzmon","orcid":"https://orcid.org/0000-0003-3817-3698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuval Atzmon","raw_affiliation_strings":["NVIDIA Research, Tel Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0003-3817-3698","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Tel Aviv, Israel","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.0616,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.98869726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"43","issue":"4","first_page":"1","last_page":"18"},"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":0.9988999962806702,"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":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958000183105469,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9664999842643738,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143573999404907},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.7438863515853882},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.6848276853561401},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6720303297042847},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5733926296234131},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5229873657226562},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5135970115661621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5076133012771606},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4985389709472656},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4862305223941803},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47638100385665894},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3959798812866211},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36586660146713257},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16239258646965027},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12200042605400085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08004838228225708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143573999404907},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.7438863515853882},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6848276853561401},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6720303297042847},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5733926296234131},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5229873657226562},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5135970115661621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076133012771606},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4985389709472656},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4862305223941803},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47638100385665894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3959798812866211},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36586660146713257},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16239258646965027},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12200042605400085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08004838228225708},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658157","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658157","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658157","source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3658157","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658157","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658157","source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400818431.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2133059825","https://openalex.org/W2603777577","https://openalex.org/W2611605760","https://openalex.org/W3014304665","https://openalex.org/W3153469116","https://openalex.org/W4289785095","https://openalex.org/W4312234230","https://openalex.org/W4385270985","https://openalex.org/W4385271055","https://openalex.org/W4385527149","https://openalex.org/W4385535331","https://openalex.org/W4386072096","https://openalex.org/W4386113271","https://openalex.org/W4389539271","https://openalex.org/W4390871980","https://openalex.org/W4390872477","https://openalex.org/W4390872556","https://openalex.org/W4390873054","https://openalex.org/W4390873135","https://openalex.org/W4390873195","https://openalex.org/W4390874393","https://openalex.org/W4400582187","https://openalex.org/W4402716004","https://openalex.org/W6600120041","https://openalex.org/W6600228633"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W3172493050","https://openalex.org/W4385420271","https://openalex.org/W4312192618","https://openalex.org/W2593798266","https://openalex.org/W4385414918"],"abstract_inverted_index":{"Text-to-image":[0],"models":[1,24],"offer":[2],"a":[3,89,108,139,155],"new":[4,44],"level":[5],"of":[6,102,141],"creative":[7],"flexibility":[8],"by":[9,97],"allowing":[10],"users":[11],"to":[12,25,41,55,70,117,127,138,164],"guide":[13],"the":[14,28,39,56,99,103],"image":[15,53],"generation":[16,96],"process":[17],"through":[18],"natural":[19],"language.":[20],"However,":[21],"using":[22],"these":[23],"consistently":[26],"portray":[27],"same":[29],"subject":[30,95,119,133,148],"across":[31],"diverse":[32],"prompts":[33,76],"remains":[34],"challenging.":[35],"Existing":[36],"approaches":[37],"fine-tune":[38],"model":[40],"teach":[42],"it":[43],"words":[45],"that":[46,92],"describe":[47],"specific":[48],"user-provided":[49],"subjects":[50],"or":[51,64],"add":[52],"conditioning":[54],"model.":[57,105],"These":[58],"methods":[59],"require":[60],"lengthy":[61],"persubject":[62],"optimization":[63,157],"large-scale":[65],"pre-training.":[66],"Moreover,":[67],"they":[68],"struggle":[69],"align":[71],"generated":[72],"images":[73],"with":[74],"text":[75,151],"and":[77,113,143,150,167],"face":[78],"difficulties":[79],"in":[80],"portraying":[81],"multiple":[82],"subjects.":[83],"Here,":[84],"we":[85,124],"present":[86],"ConsiStory":[87,137,160],",":[88],"training-free":[90,170],"approach":[91],"enables":[93],"consistent":[94],"sharing":[98],"internal":[100],"activations":[101],"pretrained":[104],"We":[106,135],"introduce":[107],"subject-driven":[109],"shared":[110],"attention":[111],"block":[112],"correspondence-based":[114],"feature":[115],"injection":[116],"promote":[118],"consistency":[120,149],"between":[121],"images.":[122],"Additionally,":[123],"develop":[125],"strategies":[126],"encourage":[128],"layout":[129],"diversity":[130],"while":[131],"maintaining":[132],"consistency.":[134],"compare":[136],"range":[140],"baselines,":[142],"demonstrate":[144],"state-of-the-art":[145],"performance":[146],"on":[147],"alignment,":[152],"without":[153],"requiring":[154],"single":[156],"step.":[158],"Finally,":[159],"can":[161],"naturally":[162],"extend":[163],"multi-subject":[165],"scenarios,":[166],"even":[168],"enable":[169],"personalization":[171],"for":[172],"common":[173],"objects.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}