{"id":"https://openalex.org/W7220788478","doi":null,"title":"Glass onion: Compositional text-to-image generation using diffusion models and LLMs","display_name":"Glass onion: Compositional text-to-image generation using diffusion models and LLMs","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W7220788478"},"language":"en","primary_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/125625","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2142/125625","pdf_url":"https://www.ideals.illinois.edu/items/132704/bitstreams/440143/data.pdf","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ideals.illinois.edu/items/132704/bitstreams/440143/data.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157752709","display_name":"Shrey Sarswat","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sarswat, Shrey","raw_affiliation_strings":["Computer Science in the Graduate College of the University of Illinois Urbana-Champaign , 2024 Urbana , Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science in the Graduate College of the University of Illinois Urbana-Champaign , 2024 Urbana , Illinois","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5157752709"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/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":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/T10036","display_name":"Advanced Neural Network Applications","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/text-to-image-generation","display_name":"text-to-image generation","score":0.9229999780654907},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8960000276565552},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9860000014305115},{"id":"https://openalex.org/keywords/prompt-decomposition","display_name":"prompt decomposition","score":0.7250000238418579},{"id":"https://openalex.org/keywords/dynamic-feedback-mechanism","display_name":"dynamic feedback mechanism","score":0.6330000162124634},{"id":"https://openalex.org/keywords/image-editing","display_name":"image editing","score":0.3400000035762787}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.39629998803138733},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.35519999265670776},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.265500009059906},{"id":"https://openalex.org/C199289684","wikidata":"https://www.wikidata.org/wiki/Q83353","display_name":"Mineralogy","level":1,"score":0.2460000067949295},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2329999953508377},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.22789999842643738},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.21950000524520874},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2176000028848648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.21170000731945038}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:www.ideals.illinois.edu:2142/125625","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2142/125625","pdf_url":"https://www.ideals.illinois.edu/items/132704/bitstreams/440143/data.pdf","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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":"Thesis"}],"best_oa_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/125625","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2142/125625","pdf_url":"https://www.ideals.illinois.edu/items/132704/bitstreams/440143/data.pdf","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220788478.pdf","grobid_xml":"https://content.openalex.org/works/W7220788478.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2342877626","https://openalex.org/W2405756170","https://openalex.org/W2432004435","https://openalex.org/W2564591810","https://openalex.org/W2626778328","https://openalex.org/W2962974533","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2964313012","https://openalex.org/W2966792645","https://openalex.org/W2970127127","https://openalex.org/W3000176874","https://openalex.org/W3034431451","https://openalex.org/W3036167779","https://openalex.org/W3111551570","https://openalex.org/W3129576130","https://openalex.org/W3162926177","https://openalex.org/W3196193831","https://openalex.org/W3214068000","https://openalex.org/W4224035735","https://openalex.org/W4226079479","https://openalex.org/W4226125322","https://openalex.org/W4226352076","https://openalex.org/W4285981784","https://openalex.org/W4312977351","https://openalex.org/W4319452911","https://openalex.org/W4323717348","https://openalex.org/W4361229539","https://openalex.org/W4366850747","https://openalex.org/W4376122449","https://openalex.org/W4378446358","https://openalex.org/W4383472654","https://openalex.org/W4386076403","https://openalex.org/W4387355666","https://openalex.org/W4387968292","https://openalex.org/W4388327564","https://openalex.org/W7133224126"],"related_works":["https://openalex.org/W7220810296","https://openalex.org/W7220781797","https://openalex.org/W7133185348","https://openalex.org/W3014049152","https://openalex.org/W7196932732","https://openalex.org/W7220750758","https://openalex.org/W6996422087","https://openalex.org/W7196992588","https://openalex.org/W7221623785","https://openalex.org/W4415796473"],"abstract_inverted_index":{"Text-to-image":[0],"generation":[1,85],"has":[2,272,311],"seen":[3],"substantial":[4],"advancements":[5,163],"in":[6,67,175,192,224,232,264,318],"recent":[7],"years,":[8],"particularly":[9],"with":[10,32,82,145,296],"the":[11,62,146,156,179,226,283,304],"advent":[12],"of":[13,131,158,167,182,228,301,306,315,329,344],"diffusion":[14],"models,":[15],"which":[16,111],"have":[17,250,288,293,325,340],"transformed":[18],"how":[19],"images":[20],"are":[21,112],"generated":[22,138],"from":[23,97],"text":[24,104],"prompts.Despite":[25],"these":[26,59],"advancements,":[27],"current":[28],"methods":[29],"often":[30],"struggle":[31],"complex":[33],"challenges":[34],"such":[35],"as":[36],"accurately":[37],"interpreting":[38],"spatial":[39],"and":[40,45,93,149,185,214,231,246,254,260,278,285,299,321,338,346],"numerical":[41],"relationships,":[42],"unusual":[43],"attributes,":[44],"logically":[46],"intricate":[47],"prompts.This":[48],"work":[49],"introduces":[50],"a":[51,124,129,187,274,313],"pioneering":[52],"experimental":[53],"approach":[54,87],"specifically":[55],"designed":[56],"to":[57,89,140,202,240,268,332,356],"tackle":[58],"complexities.Inspired":[60],"by":[61],"layered":[63],"editing":[64],"techniques":[65],"found":[66],"Adobe":[68],"Photoshop,":[69],"we":[70,122],"propose":[71],"an":[72],"iterative":[73],"framework":[74],"that":[75],"leverages":[76],"Large":[77],"Language":[78],"Models":[79],"(LLMs)":[80],"along":[81],"state-of-the-art":[83],"image":[84,139],"models.This":[86,133],"aims":[88],"create":[90],"highly":[91],"accurate":[92],"controllable":[94],"visual":[95,152,195],"representations":[96],"detailed":[98],"textual":[99],"descriptions.Our":[100],"methodology":[101],"involves":[102],"decomposing":[103],"prompts":[105,168],"into":[106,116],"structured":[107],"sub-prompts":[108],"via":[109],"LLMs,":[110],"then":[113],"sequentially":[114],"rendered":[115],"images.To":[117],"refine":[118],"this":[119,159,257,266,349],"process":[120],"further,":[121],"integrate":[123],"dynamic":[125],"feedback":[126],"mechanism":[127],"using":[128],"suite":[130],"foundational":[132],"system":[134],"meticulously":[135],"evaluates":[136],"each":[137],"ensure":[141],"it":[142],"aligns":[143],"closely":[144],"original":[147],"prompt":[148],"maintains":[150],"high":[151],"fidelity.Our":[153],"findings":[154],"demonstrate":[155],"effectiveness":[157],"approach,":[160],"showing":[161],"notable":[162],"for":[164,173,189,209,282],"specific":[165],"types":[166],"while":[169],"also":[170,238],"revealing":[171],"areas":[172],"improvement":[174],"others.This":[176],"research":[177,230,267],"underscores":[178],"considerable":[180],"potential":[181],"our":[183],"method":[184],"sets":[186],"foundation":[188],"future":[190],"explorations":[191],"enhancing":[193],"automated":[194],"content":[196],"generation.I":[197],"extend":[198,353],"my":[199,206,218,229,234,290,319,327,354,357],"heartfelt":[200],"gratitude":[201],"Professor":[203],"Svetlana":[204],"Lazebnik,":[205],"thesis":[207],"advisor,":[208],"her":[210],"unwavering":[211,323],"guidance,":[212],"support,":[213],"invaluable":[215],"expertise":[216],"throughout":[217,348],"graduate":[219,307],"program.Her":[220],"mentorship":[221],"was":[222],"pivotal":[223],"navigating":[225],"complexities":[227],"shaping":[233],"academic":[235],"growth.I":[236],"am":[237,280],"thankful":[239],"Viraj":[241],"Shah,":[242],"Sethuraman":[243],"T":[244],"V":[245],"Aiyu":[247],"Cui,":[248],"who":[249,292],"been":[251,273,312,326,341],"dedicated":[252],"mentors":[253],"collaborators":[255],"on":[256],"project.Their":[258],"insights":[259],"contributions":[261],"were":[262],"instrumental":[263],"bringing":[265],"fruition.Working":[269],"alongside":[270],"them":[271],"truly":[275],"enriching":[276],"experience,":[277],"I":[279,352],"grateful":[281],"knowledge":[284],"perspectives":[286],"they":[287],"shared.To":[289],"friends,":[291],"provided":[294],"me":[295],"endless":[297],"encouragement":[298,324],"moments":[300],"relief":[302],"amidst":[303],"rigors":[305],"study,":[308],"your":[309,322],"support":[310],"source":[314],"strength.Your":[316],"belief":[317],"abilities":[320],"pillars":[328],"support.Special":[330],"mention":[331],"Deeksha":[333],"Anand,":[334],"whose":[335],"love,":[336],"patience,":[337],"understanding":[339],"constant":[342],"sources":[343],"comfort":[345],"motivation":[347],"journey.":[350],"Additionally,":[351],"appreciation":[355],"uncles":[358]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-07T00:00:00"}