{"id":"https://openalex.org/W7204304307","doi":null,"title":"LLM-guided instance-level image manipulation with diffusion u-net cross-attention maps","display_name":"LLM-guided instance-level image manipulation with diffusion u-net cross-attention maps","publication_year":2024,"publication_date":"2024-11-25","ids":{"openalex":"https://openalex.org/W7204304307"},"language":"en","primary_location":{"id":"pmh:oai:uwe-repository.worktribe.com:13263543","doi":null,"is_oa":true,"landing_page_url":"https://uwe-repository.worktribe.com/13263543/1/LLM-guided%20instance-level%20image%20manipulation%20with%20diffusion%20u-net%20cross-attention%20maps","pdf_url":null,"source":{"id":"https://openalex.org/S4306401464","display_name":"UWE Research Repository (UWE Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I178535277","host_organization_name":"University of the West of England","host_organization_lineage":["https://openalex.org/I178535277"],"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":"Presentation / Conference Contribution"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://uwe-repository.worktribe.com/13263543/1/LLM-guided%20instance-level%20image%20manipulation%20with%20diffusion%20u-net%20cross-attention%20maps","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019587869","display_name":"Ahsan Kazmi","orcid":"https://orcid.org/0000-0001-7532-5633","observed_orcids":["https://orcid.org/0000-0001-7532-5633"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazmi, Ahsan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108299847","display_name":"Andrey Palaev","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Palaev, Andrey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148214803","display_name":"Adil Khan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Adil","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":0.0,"has_fulltext":false,"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.8740000128746033},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8659999966621399},{"id":"https://openalex.org/keywords/cross-attention-maps","display_name":"cross-attention maps","score":0.9990000128746033},{"id":"https://openalex.org/keywords/open-vocabulary-object-detection","display_name":"open-vocabulary object detection","score":0.8600000143051147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766700029373169},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6966999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6690000295639038},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6029000282287598},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.593500018119812},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5357999801635742},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.5113999843597412},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.47780001163482666},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:uwe-repository.worktribe.com:13263543","doi":null,"is_oa":true,"landing_page_url":"https://uwe-repository.worktribe.com/13263543/1/LLM-guided%20instance-level%20image%20manipulation%20with%20diffusion%20u-net%20cross-attention%20maps","pdf_url":null,"source":{"id":"https://openalex.org/S4306401464","display_name":"UWE Research Repository (UWE Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I178535277","host_organization_name":"University of the West of England","host_organization_lineage":["https://openalex.org/I178535277"],"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":"Presentation / Conference Contribution"}],"best_oa_location":{"id":"pmh:oai:uwe-repository.worktribe.com:13263543","doi":null,"is_oa":true,"landing_page_url":"https://uwe-repository.worktribe.com/13263543/1/LLM-guided%20instance-level%20image%20manipulation%20with%20diffusion%20u-net%20cross-attention%20maps","pdf_url":null,"source":{"id":"https://openalex.org/S4306401464","display_name":"UWE Research Repository (UWE Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I178535277","host_organization_name":"University of the West of England","host_organization_lineage":["https://openalex.org/I178535277"],"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":"Presentation / Conference Contribution"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402754201","https://openalex.org/W4403323942","https://openalex.org/W6947950149","https://openalex.org/W4394647764","https://openalex.org/W4303439004","https://openalex.org/W7162465976","https://openalex.org/W4405270932","https://openalex.org/W7166818276","https://openalex.org/W3217329271","https://openalex.org/W4307122275"],"abstract_inverted_index":{"The":[0],"advancement":[1],"of":[2,11,71],"text-to-image":[3],"synthesis":[4],"has":[5],"introduced":[6],"powerful":[7],"generative":[8],"models":[9],"capable":[10],"creating":[12],"realistic":[13],"images":[14,111],"from":[15],"textual":[16],"prompts.":[17],"However,":[18],"precise":[19,93,119],"control":[20,36],"over":[21],"image":[22,76],"attributes":[23],"remains":[24],"challenging,":[25],"especially":[26],"at":[27,121],"the":[28,84,89,122],"instance":[29,123],"level.":[30],"While":[31],"existing":[32],"methods":[33],"offer":[34],"some":[35],"through":[37],"fine-tuning":[38,126],"or":[39,98,127,133],"auxiliary":[40,128],"information,":[41],"they":[42],"often":[43],"face":[44],"limitations":[45],"in":[46,83,88,109],"flexibility":[47],"and":[48,65,68,86],"accuracy.":[49],"To":[50],"address":[51],"these":[52],"challenges,":[53],"we":[54],"propose":[55],"a":[56],"pipeline":[57],"leveraging":[58],"Large":[59],"Language":[60],"Models":[61],"(LLMs),":[62],"open-vocabulary":[63],"detectors":[64],"cross-attention":[66,103],"maps":[67],"intermediate":[69],"activations":[70],"diffusion":[72],"U-Net":[73],"for":[74],"instance-level":[75],"manipulation.":[77],"Our":[78,116],"method":[79],"detects":[80],"objects":[81],"mentioned":[82],"prompt":[85],"present":[87],"generated":[90],"image,":[91],"enabling":[92],"manipulation":[94],"without":[95,125],"extensive":[96],"training":[97],"input":[99],"masks.":[100],"By":[101],"incorporating":[102],"maps,":[104],"our":[105],"approach":[106,117],"ensures":[107],"coherence":[108],"manipulated":[110],"while":[112],"controlling":[113],"object":[114],"positions.":[115],"enables":[118],"manipulations":[120],"level":[124],"information":[129],"such":[130],"as":[131],"masks":[132],"bounding":[134],"boxes.":[135]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-08-27T00:00:00"}