{"id":"https://openalex.org/W7131400992","doi":"https://doi.org/10.48550/arxiv.2602.20664","title":"AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist?","display_name":"AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist?","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131400992","doi":"https://doi.org/10.48550/arxiv.2602.20664"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.20664","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003934466","display_name":"Hailong Yan","orcid":"https://orcid.org/0000-0001-5479-1264"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yan, Hailong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126842846","display_name":"Shice Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shice","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126813776","display_name":"Tao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126836007","display_name":"Xiangtao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiangtao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126831548","display_name":"Yijie Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yijie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126790330","display_name":"Jinwei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jinwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126800896","display_name":"Le Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Le","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126806234","display_name":"Bo Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5003934466"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T12290","display_name":"Human Motion and Animation","score":0.48260000348091125,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.48260000348091125,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.28690001368522644,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1251000016927719,"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/storytelling","display_name":"Storytelling","score":0.6438999772071838},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5982999801635742},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5943999886512756},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5885000228881836},{"id":"https://openalex.org/keywords/storyboard","display_name":"Storyboard","score":0.5679000020027161},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5590000152587891},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5310999751091003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533000111579895},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.6438999772071838},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5982999801635742},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C2777080924","wikidata":"https://www.wikidata.org/wiki/Q334667","display_name":"Storyboard","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5590000152587891},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4562000036239624},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45559999346733093},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3790999948978424},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.20664","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.20664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.20664","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"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.20664","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.6524608135223389,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Custom":[0],"Storyboard":[1],"Generation":[2],"(CSG)":[3],"aims":[4],"to":[5,41,91,100],"produce":[6],"high-quality,":[7],"multi-character":[8],"consistent":[9],"storytelling.":[10],"Current":[11],"approaches":[12],"based":[13],"on":[14,59],"static":[15],"diffusion":[16],"models,":[17],"whether":[18],"used":[19],"in":[20,129],"a":[21,106,117],"one-shot":[22],"manner":[23],"or":[24,52],"within":[25],"multi-agent":[26,78],"frameworks,":[27],"face":[28],"three":[29],"key":[30],"limitations:":[31],"(1)":[32],"Static":[33],"models":[34],"lack":[35],"dynamic":[36],"expressiveness":[37],"and":[38,89,103,133],"often":[39],"resort":[40],"\"copy-paste\"":[42],"pattern.":[43],"(2)":[44],"One-shot":[45],"inference":[46],"cannot":[47],"iteratively":[48],"correct":[49],"missing":[50],"attributes":[51],"poor":[53],"prompt":[54,131],"adherence.":[55],"(3)":[56],"Multi-agents":[57],"rely":[58],"non-robust":[60],"evaluators,":[61],"ill-suited":[62],"for":[63,80],"assessing":[64],"stylized,":[65],"non-realistic":[66],"animation.":[67],"To":[68],"address":[69],"these,":[70],"we":[71],"propose":[72],"AnimeAgent,":[73],"the":[74],"first":[75],"Image-to-Video":[76],"(I2V)-based":[77],"framework":[79],"CSG.":[81],"Inspired":[82],"by":[83],"Disney's":[84],"\"Combination":[85],"of":[86],"Straight":[87],"Ahead":[88],"Pose":[90],"Pose\"":[92],"workflow,":[93],"AnimeAgent":[94,125],"leverages":[95],"I2V's":[96],"implicit":[97],"motion":[98],"prior":[99],"enhance":[101],"consistency":[102],"expressiveness,":[104],"while":[105],"mixed":[107],"subjective-objective":[108],"reviewer":[109],"enables":[110],"reliable":[111],"iterative":[112],"refinement.":[113],"We":[114],"also":[115],"collect":[116],"human-annotated":[118],"CSG":[119],"benchmark":[120],"with":[121],"ground-truth.":[122],"Experiments":[123],"show":[124],"achieves":[126],"SOTA":[127],"performance":[128],"consistency,":[130],"fidelity,":[132],"stylization.":[134]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-26T00:00:00"}
