{"id":"https://openalex.org/W4361230700","doi":"https://doi.org/10.26599/cvm.2025.9450462","title":"StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing","display_name":"StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W4361230700","doi":"https://doi.org/10.26599/cvm.2025.9450462"},"language":"en","primary_location":{"id":"doi:10.26599/cvm.2025.9450462","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450462","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/cvm.2025.9450462","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102008586","display_name":"Senmao Li","orcid":"https://orcid.org/0000-0003-0377-8566"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senmao Li","raw_affiliation_strings":["College of Computer Science, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101958996","display_name":"Joost van de Weijer","orcid":"https://orcid.org/0000-0002-9656-9706"},"institutions":[{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joost Van De Weijer","raw_affiliation_strings":["The Computer Vision Center, Universitat Aut&#x00F2;noma de Barcelona,Barcelona,Spain,08193"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Computer Vision Center, Universitat Aut&#x00F2;noma de Barcelona,Barcelona,Spain,08193","institution_ids":["https://openalex.org/I71999127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070092416","display_name":"Taihang Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taihang Hu","raw_affiliation_strings":["College of Computer Science, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,UAE,20015"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,UAE,20015","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040392623","display_name":"Qibin Hou","orcid":"https://orcid.org/0000-0002-8388-8708"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibin Hou","raw_affiliation_strings":["College of Computer Science, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665190","display_name":"Yaxing Wang","orcid":"https://orcid.org/0000-0002-6055-7164"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxing Wang","raw_affiliation_strings":["College of Computer Science, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726984","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["College of Computer Science, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ming-Ming Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["College of Computer Science, Nankai University,Tianjin,China,300350"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University,Tianjin,China,300350","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.00063459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"12","issue":"3","first_page":"743","last_page":"763"},"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":0.9955000281333923,"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":0.9955000281333923,"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":0.9129999876022339,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9063000082969666,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.872923731803894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.823515772819519},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6730004549026489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5266163945198059},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5095992088317871},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4855186939239502},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4389500617980957},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33750033378601074}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.872923731803894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823515772819519},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6730004549026489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5266163945198059},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5095992088317871},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4855186939239502},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4389500617980957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33750033378601074}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.26599/cvm.2025.9450462","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450462","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2303.15649","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.15649","pdf_url":"https://arxiv.org/pdf/2303.15649","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":null,"raw_type":"text"},{"id":"pmh:oai:DiVA.org:liu-224357","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-224357","pdf_url":null,"source":{"id":"https://openalex.org/S4306400653","display_name":"Diva portal (Dalarna University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:fb30f340033745b4a43cf3b271cb7ebe","is_oa":false,"landing_page_url":"https://doaj.org/article/fb30f340033745b4a43cf3b271cb7ebe","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Visual Media, Vol 12, Iss 3, Pp 743-763 (2026)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2303.15649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2303.15649","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-journal"}],"best_oa_location":{"id":"doi:10.26599/cvm.2025.9450462","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450462","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2312145515","https://openalex.org/W4319453795","https://openalex.org/W4205104112","https://openalex.org/W1974870326","https://openalex.org/W2770776392","https://openalex.org/W3176454756","https://openalex.org/W2772330423","https://openalex.org/W3006381446","https://openalex.org/W3163523050","https://openalex.org/W4386301887"],"abstract_inverted_index":{"A":[0],"significant":[1,124],"research":[2],"effort":[3],"is":[4,96,175],"focused":[5],"on":[6,149],"exploiting":[7],"the":[8,22,26,29,33,57,64,72,85,88,93,110,130,135],"outstanding":[9],"capacities":[10],"of":[11,32,87,138,152,167],"pretrained":[12,34],"diffusion":[13],"models":[14],"for":[15,59,134],"image":[16,27],"editing.":[17],"Approaches":[18],"either":[19],"fine":[20],"tune":[21],"model,":[23],"or":[24],"invert":[25],"in":[28,45,51,71,92],"latent":[30],"space":[31],"model.":[35],"However,":[36],"they":[37],"suffer":[38],"from":[39],"two":[40,80],"problems:":[41],"(i)":[42,82],"unsatisfactory":[43],"results":[44,148],"selected":[46,53],"regions":[47],"and":[48,55,104,116,156,169],"unexpected":[49],"changes":[50],"non":[52],"regions,":[54],"(ii)":[56,105],"need":[58],"careful":[60],"text":[61],"prompt":[62,65],"editing:":[63],"should":[66],"include":[67],"all":[68],"visual":[69],"objects":[70],"input":[73,86],"image.":[74],"To":[75],"address":[76],"this,":[77],"we":[78],"propose":[79],"improvements:":[81],"only":[83],"optimizing":[84],"value":[89],"linear":[90],"network":[91],"cross-attention":[94],"layers":[95],"sufficiently":[97],"powerful":[98],"to":[99,108,165],"reconstruct":[100],"a":[101,150],"real":[102],"image,":[103],"attention":[106,112],"regularization":[107],"preserve":[109],"object-like":[111],"maps":[113],"after":[114],"reconstruction":[115],"editing,":[117],"enabling":[118],"accurate":[119],"style":[120],"editing":[121,131,162],"without":[122],"causing":[123],"structural":[125],"change.":[126],"We":[127],"further":[128],"improve":[129],"technique":[132],"used":[133,142],"unconditional":[136],"branch":[137],"classifier-free":[139],"guidance":[140],"as":[141],"by":[143],"P2P.":[144],"Extensive":[145],"experimental":[146],"prompt-editing":[147],"variety":[151],"images":[153],"demonstrate":[154],"qualitatively":[155],"quantitatively":[157],"that":[158],"our":[159],"method":[160],"has":[161],"capabilities":[163],"superior":[164],"those":[166],"existing":[168],"concurrent":[170],"works.":[171],"Our":[172],"StyleDiffusion":[173],"code":[174],"available":[176],"at":[177],"https://github.com/sen-mao/StyleDiffusion.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":10}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2023-03-31T00:00:00"}
