{"id":"https://openalex.org/W4321473567","doi":"https://doi.org/10.48550/arxiv.2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","display_name":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","publication_year":2023,"publication_date":"2023-02-20","ids":{"openalex":"https://openalex.org/W4321473567","doi":"https://doi.org/10.48550/arxiv.2302.09778"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2302.09778","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.09778","pdf_url":"https://arxiv.org/pdf/2302.09778","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2302.09778","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019994258","display_name":"Lianghua Huang","orcid":"https://orcid.org/0000-0002-9686-9354","observed_orcids":["https://orcid.org/0000-0002-9686-9354"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Lianghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368441","display_name":"Di Chen","orcid":"https://orcid.org/0000-0001-8757-3204","observed_orcids":["https://orcid.org/0000-0001-8757-3204"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004895426","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-2067-9175","observed_orcids":["https://orcid.org/0000-0002-2067-9175","https://orcid.org/0000-0001-9940-6366","https://orcid.org/0000-0002-7516-5008"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103003762","display_name":"Yujun Shen","orcid":"https://orcid.org/0000-0003-3801-6705","observed_orcids":["https://orcid.org/0000-0003-3801-6705"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yujun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":289,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","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"}},{"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-generation","display_name":"image generation","score":0.8330000042915344},{"id":"https://openalex.org/keywords/controllable-image-generation","display_name":"controllable image generation","score":0.7509999871253967},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8539999723434448},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.5289999842643738},{"id":"https://openalex.org/keywords/design-space","display_name":"design space","score":0.4339999854564667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347649335861206},{"id":"https://openalex.org/C2779674283","wikidata":"https://www.wikidata.org/wiki/Q425548","display_name":"Palette (painting)","level":2,"score":0.7114540338516235},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5963424444198608},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5037981867790222},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.501122236251831},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4572129249572754},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41770055890083313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4147481322288513},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4100160002708435},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3820306658744812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18795138597488403},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09949588775634766},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2302.09778","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.09778","pdf_url":"https://arxiv.org/pdf/2302.09778","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2302.09778","doi":"https://doi.org/10.48550/arxiv.2302.09778","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.09778","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.09778","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.09778","pdf_url":"https://arxiv.org/pdf/2302.09778","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/W4321473567.pdf","grobid_xml":"https://content.openalex.org/works/W4321473567.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4386080987","https://openalex.org/W4396882401","https://openalex.org/W4319452626","https://openalex.org/W7106682140","https://openalex.org/W7117553848","https://openalex.org/W4367191061","https://openalex.org/W4319452911","https://openalex.org/W3207932648","https://openalex.org/W4413145833","https://openalex.org/W4417088410"],"abstract_inverted_index":{"Recent":[0],"large-scale":[1],"generative":[2,166],"models":[3,172],"learned":[4],"on":[5],"big":[6],"data":[7],"are":[8],"capable":[9],"of":[10,30,103,123,164],"synthesizing":[11],"incredible":[12],"images":[13],"yet":[14],"suffer":[15],"from":[16],"limited":[17],"controllability.":[18],"This":[19],"work":[20,87],"offers":[21],"a":[22,65,93,156,161],"new":[23],"generation":[24],"paradigm":[25],"that":[26,113,152],"allows":[27],"flexible":[28],"control":[29],"the":[31,42,51,73,77,80,83,101,130,138],"output":[32],"image,":[33],"such":[34,125],"as":[35,50,72,88,126,129,137,155],"spatial":[36],"layout":[37],"and":[38,45,62,135,159,171],"palette,":[39],"while":[40],"maintaining":[41],"synthesis":[43],"quality":[44],"model":[46,67],"creativity.":[47],"With":[48],"compositionality":[49],"core":[52],"idea,":[53],"we":[54,117,150],"first":[55],"decompose":[56],"an":[57],"image":[58],"into":[59],"representative":[60],"factors,":[61],"then":[63],"train":[64],"diffusion":[66],"with":[68],"all":[69],"these":[70],"factors":[71],"conditions":[74],"to":[75,92,100],"recompose":[76],"input.":[78],"At":[79],"inference":[81],"stage,":[82],"rich":[84],"intermediate":[85],"representations":[86],"composable":[89],"elements,":[90],"leading":[91],"huge":[94],"design":[95],"space":[96],"(i.e.,":[97],"exponentially":[98],"proportional":[99],"number":[102],"decomposed":[104],"factors)":[105],"for":[106,143],"customizable":[107],"content":[108],"creation.":[109],"It":[110],"is":[111],"noteworthy":[112],"our":[114],"approach,":[115],"which":[116],"call":[118],"Composer,":[119],"supports":[120],"various":[121],"levels":[122],"conditions,":[124],"text":[127],"description":[128],"global":[131],"information,":[132],"depth":[133],"map":[134],"sketch":[136],"local":[139],"guidance,":[140],"color":[141],"histogram":[142],"low-level":[144],"details,":[145],"etc.":[146],"Besides":[147],"improving":[148],"controllability,":[149],"confirm":[151],"Composer":[153],"serves":[154],"general":[157],"framework":[158],"facilitates":[160],"wide":[162],"range":[163],"classical":[165],"tasks":[167],"without":[168],"retraining.":[169],"Code":[170],"will":[173],"be":[174],"made":[175],"available.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":87},{"year":2024,"cited_by_count":121},{"year":2023,"cited_by_count":49}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-02-23T00:00:00"}
