{"id":"https://openalex.org/W4388514904","doi":"https://doi.org/10.48550/arxiv.2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","display_name":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388514904","doi":"https://doi.org/10.48550/arxiv.2311.04145"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.04145","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04145","pdf_url":"https://arxiv.org/pdf/2311.04145","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/2311.04145","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100449697","display_name":"Shiwei Zhang","orcid":"https://orcid.org/0000-0002-6929-5295","observed_orcids":["https://orcid.org/0000-0002-6929-5295","https://orcid.org/0000-0003-2870-3974"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368334","display_name":"Jiayu Wang","orcid":"https://orcid.org/0000-0003-4497-2891","observed_orcids":["https://orcid.org/0000-0003-4497-2891"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039538233","display_name":"Yingya Zhang","orcid":"https://orcid.org/0009-0008-9524-9218","observed_orcids":["https://orcid.org/0009-0008-9524-9218"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yingya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103326213","display_name":"Kang Zhao","orcid":"https://orcid.org/0009-0000-3053-3965","observed_orcids":["https://orcid.org/0009-0000-3053-3965"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080934752","display_name":"Hangjie Yuan","orcid":"https://orcid.org/0009-0009-3270-1526","observed_orcids":["https://orcid.org/0009-0009-3270-1526"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan, Hangjie","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053138623","display_name":"Zhiwu Qin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin, Zhiwu","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389037","display_name":"Xiang Wang","orcid":"https://orcid.org/0000-0002-6148-6329","observed_orcids":["https://orcid.org/0000-0002-6148-6329","https://orcid.org/0000-0002-2312-0166"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xiang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911374","display_name":"Deli Zhao","orcid":"https://orcid.org/0000-0002-8838-578X","observed_orcids":["https://orcid.org/0000-0002-8838-578X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Deli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634","observed_orcids":["https://orcid.org/0000-0002-4220-2634"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jingren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":322,"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":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0,"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/image-to-video-synthesis","display_name":"image-to-video synthesis","score":0.9890000224113464},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8539999723434448},{"id":"https://openalex.org/keywords/video-text-alignment","display_name":"video-text alignment","score":0.7609999775886536},{"id":"https://openalex.org/keywords/hierarchical-encoder","display_name":"hierarchical encoder","score":0.6589999794960022},{"id":"https://openalex.org/keywords/spatiotemporal-continuity","display_name":"spatiotemporal continuity","score":0.8019999861717224},{"id":"https://openalex.org/keywords/semantic-accuracy","display_name":"semantic accuracy","score":0.6230000257492065},{"id":"https://openalex.org/keywords/image-text-pairs","display_name":"image-text pairs","score":0.5440000295639038}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8182390928268433},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.664417028427124},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.5057225227355957},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4571130573749542},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4395676255226135},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37728723883628845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35437679290771484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16257533431053162},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.04145","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04145","pdf_url":"https://arxiv.org/pdf/2311.04145","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.2311.04145","doi":"https://doi.org/10.48550/arxiv.2311.04145","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.04145","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:2311.04145","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04145","pdf_url":"https://arxiv.org/pdf/2311.04145","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/W4388514904.pdf","grobid_xml":"https://content.openalex.org/works/W4388514904.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2908510526","https://openalex.org/W3092442149","https://openalex.org/W3110257065","https://openalex.org/W3209532394","https://openalex.org/W4221146061","https://openalex.org/W4221149884","https://openalex.org/W4224035735","https://openalex.org/W4226057201","https://openalex.org/W4281632497","https://openalex.org/W4283009758","https://openalex.org/W4287029626","https://openalex.org/W4298185919","https://openalex.org/W4303440777","https://openalex.org/W4309800375","https://openalex.org/W4320184687","https://openalex.org/W4321473567","https://openalex.org/W4378506819","https://openalex.org/W4378945677","https://openalex.org/W4383472654","https://openalex.org/W4385327921","https://openalex.org/W4385848606","https://openalex.org/W4385965594","https://openalex.org/W4386057725","https://openalex.org/W4387195417","https://openalex.org/W4388093548","https://openalex.org/W4390874580","https://openalex.org/W4391807605","https://openalex.org/W4402702999","https://openalex.org/W4403003238","https://openalex.org/W4405695475","https://openalex.org/W7133199008"],"related_works":["https://openalex.org/W4399418315","https://openalex.org/W4416924568","https://openalex.org/W4409365504","https://openalex.org/W4405695475","https://openalex.org/W7160898368","https://openalex.org/W4410773559","https://openalex.org/W4413157934","https://openalex.org/W4386071957","https://openalex.org/W4404088608","https://openalex.org/W7117970227"],"abstract_inverted_index":{"Video":[0],"synthesis":[1],"has":[2],"recently":[3],"made":[4],"remarkable":[5],"strides":[6],"benefiting":[7],"from":[8,32,110],"the":[9,33,40,50,79,82,101,120,124,135,141,158,167,184],"rapid":[10],"development":[11],"of":[12,22,35,44,81,92,97,171,175,187],"diffusion":[13],"models.":[14],"However,":[15],"it":[16,47,191],"still":[17],"encounters":[18],"challenges":[19],"in":[20],"terms":[21],"semantic":[23,55,168],"accuracy,":[24,169],"clarity":[25,174],"and":[26,39,56,77,107,118,133,151,173,189,207],"spatio-temporal":[27],"continuity.":[28],"They":[29],"primarily":[30],"arise":[31],"scarcity":[34],"well-aligned":[36],"text-video":[37,149],"data":[38,84],"complex":[41],"inherent":[42],"structure":[43],"videos,":[45],"making":[46],"difficult":[48],"for":[49],"model":[51,70],"to":[52,137,156],"simultaneously":[53,165],"ensure":[54],"qualitative":[57],"excellence.":[58],"In":[59],"this":[60,161],"report,":[61],"we":[62,143,181],"propose":[63],"a":[64,90],"cascaded":[65],"I2VGen-XL":[66,95,163,188],"approach":[67],"that":[68],"enhances":[69,123],"performance":[71],"by":[72,85,113,127],"decoupling":[73],"these":[74],"two":[75,98,115],"factors":[76],"ensures":[78],"alignment":[80],"input":[83,111],"utilizing":[86],"static":[87],"images":[88,112],"as":[89],"form":[91],"crucial":[93],"guidance.":[94],"consists":[96],"stages:":[99],"i)":[100],"base":[102],"stage":[103,122],"guarantees":[104],"coherent":[105],"semantics":[106],"preserves":[108],"content":[109],"using":[114],"hierarchical":[116],"encoders,":[117],"ii)":[119],"refinement":[121],"video's":[125],"details":[126,172],"incorporating":[128],"an":[129],"additional":[130],"brief":[131],"text":[132],"improves":[134],"resolution":[136],"1280$\\times$720.":[138],"To":[139],"improve":[140],"diversity,":[142],"collect":[144],"around":[145],"35":[146],"million":[147],"single-shot":[148],"pairs":[150,155],"6":[152],"billion":[153],"text-image":[154],"optimize":[157],"model.":[159],"By":[160],"means,":[162],"can":[164,197],"enhance":[166],"continuity":[170],"generated":[176],"videos.":[177],"Through":[178],"extensive":[179],"experiments,":[180],"have":[182],"investigated":[183],"underlying":[185],"principles":[186],"compared":[190],"with":[192],"current":[193],"top":[194],"methods,":[195],"which":[196],"demonstrate":[198],"its":[199],"effectiveness":[200],"on":[201],"diverse":[202],"data.":[203],"The":[204],"source":[205],"code":[206],"models":[208],"will":[209],"be":[210],"publicly":[211],"available":[212],"at":[213],"\\url{https://i2vgen-xl.github.io}.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":78},{"year":2025,"cited_by_count":140},{"year":2024,"cited_by_count":99},{"year":2023,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-11-09T00:00:00"}