{"id":"https://openalex.org/W4378942574","doi":"https://doi.org/10.48550/arxiv.2305.18583","title":"Controllable Text-to-Image Generation with GPT-4","display_name":"Controllable Text-to-Image Generation with GPT-4","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4378942574","doi":"https://doi.org/10.48550/arxiv.2305.18583"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.18583","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.18583","pdf_url":"https://arxiv.org/pdf/2305.18583","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.18583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101571114","display_name":"Tianjun Zhang","orcid":"https://orcid.org/0000-0003-2059-0709","observed_orcids":["https://orcid.org/0000-0003-2059-0709"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tianjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Yi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045147286","display_name":"Vibhav Vineet","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vineet, Vibhav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072006037","display_name":"Neel Joshi","orcid":"https://orcid.org/0000-0001-8236-3566","observed_orcids":["https://orcid.org/0000-0001-8236-3566"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joshi, Neel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621693","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0003-4854-3939","observed_orcids":["https://orcid.org/0000-0003-4854-3939"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xin","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":false,"cited_by_count":9,"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":0.996999979019165},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.878000020980835},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8180000185966492},{"id":"https://openalex.org/keywords/controlnet","display_name":"ControlNet","score":0.9929999709129333},{"id":"https://openalex.org/keywords/instruction-following","display_name":"instruction following","score":0.7279999852180481},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/controllable-image-generation","display_name":"controllable image generation","score":0.7059999704360962},{"id":"https://openalex.org/keywords/photorealistic-images","display_name":"photorealistic images","score":0.6159999966621399},{"id":"https://openalex.org/keywords/object-placement","display_name":"object placement","score":0.6330000162124634}],"concepts":[{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.7696461081504822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7344086766242981},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6632668972015381},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5646105408668518},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5425328612327576},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5378984212875366},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5238180756568909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3853186368942261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.360612154006958},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3291248679161072},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2126496136188507},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.18583","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.18583","pdf_url":"https://arxiv.org/pdf/2305.18583","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.2305.18583","doi":"https://doi.org/10.48550/arxiv.2305.18583","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.18583","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:2305.18583","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.18583","pdf_url":"https://arxiv.org/pdf/2305.18583","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":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4398163699","https://openalex.org/W4417267284","https://openalex.org/W7005855574","https://openalex.org/W4388187930","https://openalex.org/W7155440220","https://openalex.org/W4415754475","https://openalex.org/W6929605367","https://openalex.org/W4367190568","https://openalex.org/W4416543436","https://openalex.org/W4390873211"],"abstract_inverted_index":{"Current":[0],"text-to-image":[1,54],"generation":[2,161],"models":[3,91],"often":[4],"struggle":[5],"to":[6,50,73,94,101,130,190],"follow":[7],"textual":[8],"instructions,":[9],"especially":[10],"the":[11,17,52,78,86,106,119,132,144,155,173,185,192],"ones":[12],"requiring":[13],"spatial":[14,156],"reasoning.":[15],"On":[16],"other":[18],"hand,":[19],"Large":[20],"Language":[21],"Models":[22],"(LLMs),":[23],"such":[24],"as":[25,83,180],"GPT-4,":[26,61],"have":[27],"shown":[28],"remarkable":[29],"precision":[30],"in":[31,125,194],"generating":[32],"code":[33],"snippets":[34],"for":[35,65,89,187],"sketching":[36],"out":[37],"text":[38,87],"inputs":[39],"graphically,":[40],"e.g.,":[41],"via":[42],"TikZ.":[43],"In":[44],"this":[45],"work,":[46,179],"we":[47],"introduce":[48],"Control-GPT":[49,68,141],"guide":[51],"diffusion-based":[53],"pipelines":[55],"with":[56],"programmatic":[57],"sketches":[58,80,133],"generated":[59,79],"by":[60,70,121],"enhancing":[62],"their":[63],"abilities":[64],"instruction":[66],"following.":[67],"works":[69],"querying":[71],"GPT-4":[72],"write":[74],"TikZ":[75],"code,":[76],"and":[77,115,158,162],"are":[81],"used":[82,134],"references":[84],"alongside":[85],"instructions":[88],"diffusion":[90],"(e.g.,":[92],"ControlNet)":[93],"generate":[95],"photo-realistic":[96],"images.":[97],"One":[98],"major":[99],"challenge":[100],"training":[102],"our":[103],"pipeline":[104],"is":[105],"lack":[107],"of":[108,146,166,175],"a":[109,139,151,181],"dataset":[110],"containing":[111],"aligned":[112],"text,":[113],"images,":[114],"sketches.":[116],"We":[117],"address":[118],"issue":[120],"converting":[122],"instance":[123],"masks":[124],"existing":[126],"datasets":[127],"into":[128],"polygons":[129],"mimic":[131],"at":[135],"test":[136],"time.":[137],"As":[138],"result,":[140],"greatly":[142],"boosts":[143],"controllability":[145],"image":[147],"generation.":[148],"It":[149],"establishes":[150],"new":[152],"state-of-art":[153],"on":[154],"arrangement":[157],"object":[159,167],"positioning":[160],"enhances":[163],"users'":[164],"control":[165],"positions,":[168],"sizes,":[169],"etc.,":[170],"nearly":[171],"doubling":[172],"accuracy":[174],"prior":[176],"models.":[177],"Our":[178],"first":[182],"attempt,":[183],"shows":[184],"potential":[186],"employing":[188],"LLMs":[189],"enhance":[191],"performance":[193],"computer":[195],"vision":[196],"tasks.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2023-06-01T00:00:00"}