{"id":"https://openalex.org/W7127445971","doi":"https://doi.org/10.48550/arxiv.2602.01303","title":"ReDiStory: Region-Disentangled Diffusion for Consistent Visual Story Generation","display_name":"ReDiStory: Region-Disentangled Diffusion for Consistent Visual Story Generation","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7127445971","doi":"https://doi.org/10.48550/arxiv.2602.01303"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.01303","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.01303","pdf_url":"https://arxiv.org/pdf/2602.01303","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.01303","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124958693","display_name":"Ayushman Sarkar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarkar, Ayushman","raw_affiliation_strings":["Birbhum Institute of Engineering and Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birbhum Institute of Engineering and Technology ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124919916","display_name":"Zhenyu Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Yu, Zhenyu","raw_affiliation_strings":["Universiti Malaya ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Malaya ,","institution_ids":["https://openalex.org/I33849332"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124943769","display_name":"Chu Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen, Chu","raw_affiliation_strings":["City University of Hong Kong ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong ,","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135644833","display_name":"Wei Tang","orcid":"https://orcid.org/0000-0001-5739-4168","observed_orcids":["https://orcid.org/0000-0001-5739-4168"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tang, Wei","raw_affiliation_strings":["City University of Hong Kong ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong ,","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146529162","display_name":"Kangning Cui","orcid":"https://orcid.org/0000-0002-1856-5064","observed_orcids":["https://orcid.org/0000-0002-1856-5064"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Cui, Kangning","raw_affiliation_strings":["City University of Hong Kong ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong ,","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124913157","display_name":"Mohd Yamani Idna Idris","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Idris, Mohd Yamani Idna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T14254","display_name":"Digital Media and Visual Art","score":0.0,"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/diffusion-models","display_name":"diffusion models","score":0.6489999890327454},{"id":"https://openalex.org/keywords/identity-consistency","display_name":"identity consistency","score":0.5879999995231628},{"id":"https://openalex.org/keywords/training-free-methods","display_name":"training-free methods","score":0.640999972820282},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.7878000140190125},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6862000226974487},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5497000217437744},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5278000235557556},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47600001096725464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4336000084877014},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32010000944137573},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C3019760831","wikidata":"https://www.wikidata.org/wiki/Q5300012","display_name":"Double diffusion","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.01303","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.01303","pdf_url":"https://arxiv.org/pdf/2602.01303","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2602.01303","doi":"https://doi.org/10.48550/arxiv.2602.01303","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.01303","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.01303","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.01303","pdf_url":"https://arxiv.org/pdf/2602.01303","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127445971.pdf","grobid_xml":"https://content.openalex.org/works/W7127445971.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4383472654","https://openalex.org/W4385848774","https://openalex.org/W7133220105"],"related_works":["https://openalex.org/W7127284498","https://openalex.org/W7204536841","https://openalex.org/W7163918612","https://openalex.org/W7138145951","https://openalex.org/W7222718942","https://openalex.org/W7162108609","https://openalex.org/W7139094439","https://openalex.org/W7117851306","https://openalex.org/W7165911827","https://openalex.org/W7125958184"],"abstract_inverted_index":{"Generating":[0],"coherent":[1],"visual":[2],"stories":[3],"requires":[4],"maintaining":[5,101],"subject":[6],"identity":[7,19,36,98,116],"across":[8,75],"multiple":[9,115],"images":[10],"while":[11,100],"preserving":[12],"frame-specific":[13,65],"semantics.":[14],"Recent":[15],"training-free":[16,45],"methods":[17],"concatenate":[18],"and":[20,64,93],"frame":[21,69],"prompts":[22],"into":[23,62],"a":[24,44],"unified":[25],"representation,":[26],"but":[27],"this":[28],"often":[29],"introduces":[30],"inter-frame":[31],"semantic":[32],"interference":[33,80],"that":[34,47],"weakens":[35],"preservation":[37],"in":[38],"complex":[39],"stories.":[40],"We":[41],"propose":[42],"ReDiStory,":[43],"framework":[46],"improves":[48,97],"multi-frame":[49],"story":[50],"generation":[51],"via":[52],"inference-time":[53],"prompt":[54,102],"embedding":[55],"reorganization.":[56],"ReDiStory":[57,96],"explicitly":[58],"decomposes":[59],"text":[60],"embeddings":[61,70],"identity-related":[63],"components,":[66],"then":[67],"decorrelates":[68],"by":[71],"suppressing":[72],"shared":[73],"directions":[74],"frames.":[76],"This":[77],"reduces":[78],"cross-frame":[79],"without":[81],"modifying":[82],"diffusion":[83,91],"parameters":[84],"or":[85],"requiring":[86],"additional":[87],"supervision.":[88],"Under":[89],"identical":[90],"backbones":[92],"inference":[94],"settings,":[95],"consistency":[99,117],"fidelity.":[103],"Experiments":[104],"on":[105,114],"the":[106],"ConsiStory+":[107],"benchmark":[108],"show":[109],"consistent":[110],"gains":[111],"over":[112],"1Prompt1Story":[113],"metrics.":[118],"Code":[119],"is":[120],"available":[121],"at:":[122],"https://github.com/YuZhenyuLindy/ReDiStory":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-04T00:00:00"}