{"id":"https://openalex.org/W4402777371","doi":"https://doi.org/10.1109/cvpr52733.2024.00763","title":"TextCraftor: Your Text Encoder can be Image Quality Controller","display_name":"TextCraftor: Your Text Encoder can be Image Quality Controller","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402777371","doi":"https://doi.org/10.1109/cvpr52733.2024.00763"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010773732","display_name":"Yanyu Li","orcid":"https://orcid.org/0000-0003-1240-4785"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanyu Li","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101593882","display_name":"Xian Liu","orcid":"https://orcid.org/0000-0003-0075-0824"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xian Liu","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081874764","display_name":"Anil Kag","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anil Kag","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101001123","display_name":"Hu Ju","orcid":"https://orcid.org/0009-0006-1260-9931"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ju Hu","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000781425","display_name":"Yerlan Idelbayev","orcid":"https://orcid.org/0000-0002-0179-467X"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yerlan Idelbayev","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114232689","display_name":"Dhritiman Sagar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhritiman Sagar","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651384","display_name":"Yanzhi Wang","orcid":"https://orcid.org/0000-0002-3024-7990"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Yanzhi Wang","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112864934","display_name":"Sergey Tulyakov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Tulyakov","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101823378","display_name":"Jian Ren","orcid":"https://orcid.org/0000-0001-7924-9586"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Ren","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7985","last_page":"7995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.46369999647140503,"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"}},"topics":[{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.46369999647140503,"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/T13674","display_name":"Computer Science and Engineering","score":0.40310001373291016,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7309749126434326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6405622959136963},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5387545228004456},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5249219536781311},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4778865575790405},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4616734981536865},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4389815330505371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4059072434902191},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09012988209724426},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0633564293384552},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.05485105514526367}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7309749126434326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6405622959136963},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5387545228004456},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5249219536781311},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4778865575790405},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4616734981536865},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4389815330505371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059072434902191},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09012988209724426},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0633564293384552},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.05485105514526367},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2334580170"],"abstract_inverted_index":{"Diffusion-based":[0],"text-to-image":[1,91,114],"generative":[2,193],"models,":[3,77,136],"e.g.,":[4],"Stable":[5,130],"Diffusion,":[6],"have":[7,70],"revolutionized":[8],"the":[9,48,74,106,111,124,166],"field":[10],"of":[11,90,113,122,168],"content":[12],"generation,":[13],"enabling":[14],"significant":[15],"advancements":[16],"in":[17,129,151],"areas":[18],"like":[19],"image":[20,43,163],"editing":[21],"and":[22,51,102,154,186],"video":[23],"synthesis.":[24],"Despite":[25],"their":[26,34],"formidable":[27],"capabilities,":[28],"these":[29,66,85],"models":[30],"are":[31,58],"not":[32],"without":[33],"limitations.":[35],"It":[36],"is":[37,181],"still":[38],"challenging":[39],"to":[40,60,72,104,109,148,183,190],"synthesize":[41],"an":[42],"that":[44,179],"aligns":[45],"well":[46],"with":[47,54,132,173],"input":[49],"text,":[50],"multiple":[52],"runs":[53],"carefully":[55],"crafted":[56],"prompts":[57],"required":[59],"achieve":[61],"satisfactory":[62],"results.":[63],"To":[64],"mitigate":[65],"limitations,":[67],"numerous":[68],"studies":[69],"endeavored":[71],"fine-tune":[73,105],"pre-trained":[75],"diffusion":[76,92,115],"i.e.,":[78],"UNet,":[79],"utilizing":[80],"various":[81,174],"technologies.":[82],"Yet,":[83],"amidst":[84],"efforts,":[86],"a":[87],"pivotal":[88],"question":[89],"model":[93],"training":[94],"has":[95],"remained":[96],"largely":[97],"unexplored:":[98],"Is":[99],"it":[100,140],"possible":[101],"feasible":[103],"text":[107,126,170],"encoder":[108,127],"improve":[110,192],"performance":[112],"models?":[116],"Our":[117],"findings":[118],"reveal":[119],"that,":[120],"instead":[121],"replacing":[123],"CLIP":[125],"used":[128],"Diffusion":[131],"other":[133],"large":[134],"language":[135],"we":[137],"can":[138,187],"enhance":[139],"through":[141,165],"our":[142,158],"proposed":[143],"fine-tuning":[144],"approach,":[145],"TextCraftor,":[146],"leading":[147],"substantial":[149],"improvements":[150],"quantitative":[152],"benchmarks":[153],"human":[155],"assessments.":[156],"Interestingly,":[157],"technique":[159],"also":[160,177],"empowers":[161],"controllable":[162],"generation":[164],"interpolation":[167],"different":[169],"encoders":[171],"fine-tuned":[172],"rewards.":[175],"We":[176],"demonstrate":[178],"TextCraftor":[180],"orthogonal":[182],"UNet":[184],"finetuning,":[185],"be":[188],"combined":[189],"further":[191],"quality.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}