{"id":"https://openalex.org/W7217722196","doi":null,"title":"Pictorama: Text based Image Editing using Diffusion Model","display_name":"Pictorama: Text based Image Editing using Diffusion Model","publication_year":2024,"publication_date":"2024-03-26","ids":{"openalex":"https://openalex.org/W7217722196"},"language":"en","primary_location":{"id":"pmh:oai:www.ijisae.org:article/5435","doi":null,"is_oa":true,"landing_page_url":"https://ijisae.org/index.php/IJISAE/article/view/5435","pdf_url":"https://ijisae.org/index.php/IJISAE/article/download/5435/4161","source":{"id":"https://openalex.org/S2764360368","display_name":"International Journal of Intelligent Systems and Applications in Engineering","issn_l":"2147-6799","issn":["2147-6799"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","poland-20","russia-white-list-4"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2147-6799","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ijisae.org/index.php/IJISAE/article/download/5435/4161","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5155081221","display_name":"Vishal Mamluskar, Allen Lopes, Nesan Selvan, Teena Varma, Harshali Patil, Kavita Jain, Deepali Vora, Akash Sawant,","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vishal Mamluskar, Allen Lopes, Nesan Selvan, Teena Varma, Harshali Patil, Kavita Jain, Deepali Vora, Akash Sawant,","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5155081221"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.0,"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/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/text-to-image-editing","display_name":"text-to-image editing","score":0.9100000262260437},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.6830000281333923},{"id":"https://openalex.org/keywords/disentanglement","display_name":"disentanglement","score":0.8629999756813049},{"id":"https://openalex.org/keywords/inference-speed","display_name":"inference speed","score":0.39100000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8662999868392944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5598999857902527},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4465999901294708},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4375},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.38429999351501465},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3555000126361847},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:www.ijisae.org:article/5435","doi":null,"is_oa":true,"landing_page_url":"https://ijisae.org/index.php/IJISAE/article/view/5435","pdf_url":"https://ijisae.org/index.php/IJISAE/article/download/5435/4161","source":{"id":"https://openalex.org/S2764360368","display_name":"International Journal of Intelligent Systems and Applications in Engineering","issn_l":"2147-6799","issn":["2147-6799"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","poland-20","russia-white-list-4"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2147-6799","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:www.ijisae.org:article/5435","doi":null,"is_oa":true,"landing_page_url":"https://ijisae.org/index.php/IJISAE/article/view/5435","pdf_url":"https://ijisae.org/index.php/IJISAE/article/download/5435/4161","source":{"id":"https://openalex.org/S2764360368","display_name":"International Journal of Intelligent Systems and Applications in Engineering","issn_l":"2147-6799","issn":["2147-6799"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","poland-20","russia-white-list-4"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2147-6799","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7217722196.pdf","grobid_xml":"https://content.openalex.org/works/W7217722196.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2992838650","https://openalex.org/W3048372515","https://openalex.org/W3141117710","https://openalex.org/W3162926177","https://openalex.org/W3214068000","https://openalex.org/W4225323055","https://openalex.org/W4289785095","https://openalex.org/W4312388283","https://openalex.org/W4312911498","https://openalex.org/W4383174279","https://openalex.org/W4385328204","https://openalex.org/W4386057725","https://openalex.org/W4386075490","https://openalex.org/W4386076215","https://openalex.org/W4390872387","https://openalex.org/W4409262782"],"related_works":["https://openalex.org/W4402715857","https://openalex.org/W4405270932","https://openalex.org/W4386908010","https://openalex.org/W4414490197","https://openalex.org/W4321854185","https://openalex.org/W4415798725","https://openalex.org/W4405562514","https://openalex.org/W4393160345","https://openalex.org/W4390873319","https://openalex.org/W4392271989"],"abstract_inverted_index":{"This":[0,260],"research":[1,129,261],"aims":[2],"to":[3,24,33,102,166,218,253],"pioneer":[4],"image":[5,29,42,107,126,200,250,272],"modification":[6],"through":[7],"text,":[8],"integrating":[9,64],"natural":[10],"language":[11,27],"descriptions":[12],"with":[13,109,173,182,232],"advanced":[14],"computer":[15],"vision":[16],"and":[17,28,52,62,91,118,124,147,156,248,270],"NLP":[18],"techniques.":[19],"The":[20,44,72,113,128,144,202,238],"primary":[21],"objective":[22],"is":[23,74,214],"bridge":[25],"human":[26],"editing,":[30],"empowering":[31],"users":[32],"convey":[34],"creative":[35],"visions":[36],"effortlessly,":[37],"revolutionizing":[38],"the":[39,177,180,209,219,254,275],"field":[40],"of":[41,79,185,204,206,222,235,257,277],"modification.":[43],"study":[45,239],"employs":[46],"stable":[47,132],"diffusion":[48,133],"models,":[49],"leveraging":[50],"PyTorch":[51],"Python.":[53],"It":[54],"builds":[55],"on":[56,76,208],"prior":[57],"works":[58],"like":[59],"Imagic,":[60],"LEDITS,":[61],"Instructpix2pix,":[63],"a":[65,77,230],"novel":[66,263],"Vector":[67],"Quantized":[68],"Diffusion":[69,120],"(VQ-Diffusion)":[70],"model.":[71],"model":[73,181],"trained":[75],"dataset":[78],"436":[80],"GB":[81,234],"containing":[82],"3":[83],"features":[84],"an":[85,88,92],"input":[86],"image,":[87],"editing":[89],"instruction,":[90],"output":[93,171],"edited":[94],"image.":[95,178],"Test":[96],"samples":[97],"include":[98],"real":[99],"images":[100,172],"subjected":[101],"diverse":[103],"text":[104,116],"prompts":[105],"for":[106,122,188,198,212,226],"edits,":[108],"disentanglement":[110,136],"properties":[111],"explored.":[112],"approach":[114],"combines":[115],"inversion":[117],"Box-Constrained":[119],"(BoxDiff)":[121],"personalized":[123],"conditional":[125],"synthesis.":[127,259],"showcases":[130],"that":[131],"models":[134,149],"exhibit":[135],"properties,":[137],"enabling":[138],"effective":[139],"modifications":[140],"without":[141],"extensive":[142],"fine-tuning.":[143],"introduced":[145],"BoxDiff":[146],"VQ-Diffusion":[148],"demonstrate":[150],"superior":[151],"performance":[152],"in":[153,170,190,265],"spatially":[154,267],"constrained":[155,268],"complex":[157],"scene":[158],"synthesis,":[159,269],"outperforming":[160],"traditional":[161],"methods.":[162],"We":[163],"are":[164],"able":[165],"observe":[167],"greater":[168,183,199],"quality":[169],"good":[174],"cohesiveness":[175],"throughout":[176],"Runing":[179],"number":[184,205],"steps":[186,197,207],"allows":[187],"upheaval":[189],"quality.":[191,201],"Here":[192],"we":[193,228],"have":[194],"used":[195],"100":[196],"effect":[203],"time":[210],"taken":[211],"inference":[213],"also":[215],"studied.":[216],"Due":[217],"large":[220],"amount":[221],"video":[223,236],"memory":[224],"required":[225],"inferencing,":[227],"recommend":[229],"GPU":[231],">11":[233],"memory.":[237],"adds":[240],"value":[241],"by":[242],"addressing":[243],"biases,":[244],"achieving":[245],"higher":[246],"speeds,":[247],"enhancing":[249],"quality,":[251],"contributing":[252],"evolving":[255],"landscape":[256],"text-to-image":[258,278],"introduces":[262],"approaches":[264],"disentanglement,":[266],"rapid":[271],"generation,":[273],"pushing":[274],"boundaries":[276],"synthesis":[279],"beyond":[280],"existing":[281],"limitations.":[282]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}