{"id":"https://openalex.org/W4404355339","doi":"https://doi.org/10.48550/arxiv.2411.02395","title":"Training-free Regional Prompting for Diffusion Transformers","display_name":"Training-free Regional Prompting for Diffusion Transformers","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404355339","doi":"https://doi.org/10.48550/arxiv.2411.02395"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.02395","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02395","pdf_url":"https://arxiv.org/pdf/2411.02395","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.02395","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087171054","display_name":"Anthony Chen","orcid":"https://orcid.org/0000-0003-4363-5041","observed_orcids":["https://orcid.org/0000-0003-4363-5041"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Anthony","raw_affiliation_strings":["InstantX Team ,","Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InstantX Team ,","institution_ids":[]},{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102857716","display_name":"Jianjin Xu","orcid":"https://orcid.org/0000-0002-1951-9772","observed_orcids":["https://orcid.org/0000-0002-1951-9772"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Jianjin","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006396086","display_name":"Wenzhao Zheng","orcid":"https://orcid.org/0000-0001-7188-3734","observed_orcids":["https://orcid.org/0000-0001-7188-3734"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng, Wenzhao","raw_affiliation_strings":["UC Berkeley ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley ,","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dai, Gaole","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dai, Gaole","raw_affiliation_strings":["Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638214","display_name":"Yida Wang","orcid":"https://orcid.org/0000-0001-8165-840X","observed_orcids":["https://orcid.org/0000-0001-8165-840X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yida","raw_affiliation_strings":["Li Auto Inc. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto Inc. ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891082","display_name":"Renrui Zhang","orcid":"https://orcid.org/0000-0003-4503-5277","observed_orcids":["https://orcid.org/0000-0003-4503-5277"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhang, Renrui","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041138115","display_name":"Haofan Wang","orcid":"https://orcid.org/0009-0001-9856-3666","observed_orcids":["https://orcid.org/0009-0001-9856-3666"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haofan","raw_affiliation_strings":["InstantX Team ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InstantX Team ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013030532","display_name":"Shanghang Zhang","orcid":"https://orcid.org/0000-0003-4047-3526","observed_orcids":["https://orcid.org/0000-0003-4047-3526"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Shanghang","raw_affiliation_strings":["Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":29,"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":9.999999747378752e-05,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0,"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/diffusion-transformer","display_name":"diffusion transformer","score":0.7250000238418579},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.8360000252723694},{"id":"https://openalex.org/keywords/flux-1","display_name":"FLUX.1","score":0.7789999842643738},{"id":"https://openalex.org/keywords/attention-manipulation","display_name":"attention manipulation","score":0.6949999928474426},{"id":"https://openalex.org/keywords/compositional-image-generation","display_name":"compositional image generation","score":0.8080000281333923}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4810250401496887},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4615848660469055},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.40149828791618347},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.23723837733268738},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2336786985397339},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2170065939426422},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.061011552810668945},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.04832535982131958}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.02395","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02395","pdf_url":"https://arxiv.org/pdf/2411.02395","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.2411.02395","doi":"https://doi.org/10.48550/arxiv.2411.02395","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.02395","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:2411.02395","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02395","pdf_url":"https://arxiv.org/pdf/2411.02395","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404355339.pdf","grobid_xml":"https://content.openalex.org/works/W4404355339.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2972677740","https://openalex.org/W4287265459","https://openalex.org/W4319452911","https://openalex.org/W4383472654","https://openalex.org/W4384918448","https://openalex.org/W4388685775","https://openalex.org/W4396822569","https://openalex.org/W4399597888","https://openalex.org/W4400601342","https://openalex.org/W4403321890","https://openalex.org/W4403705225","https://openalex.org/W4404625217","https://openalex.org/W7051896053"],"related_works":["https://openalex.org/W7220723695","https://openalex.org/W4402727926","https://openalex.org/W7128400020","https://openalex.org/W4378446358","https://openalex.org/W7125193831","https://openalex.org/W7170082184","https://openalex.org/W4390306967","https://openalex.org/W7170082782","https://openalex.org/W4390897529","https://openalex.org/W7082629842"],"abstract_inverted_index":{"Diffusion":[0,77],"models":[1,24,30,64],"have":[2,59],"demonstrated":[3],"excellent":[4],"capabilities":[5],"in":[6,109],"text-to-image":[7,106],"generation.":[8],"Their":[9],"semantic":[10],"understanding":[11],"(i.e.,":[12],"prompt":[13],"following)":[14],"ability":[15],"has":[16],"also":[17],"been":[18,60],"greatly":[19],"improved":[20],"with":[21,47,103],"large":[22],"language":[23],"(e.g.,":[25],"T5,":[26],"Llama).":[27],"However,":[28],"existing":[29],"cannot":[31],"perfectly":[32],"handle":[33],"long":[34],"and":[35,50,84,90],"complex":[36],"text":[37,42],"prompts,":[38],"especially":[39],"when":[40],"the":[41,75],"prompts":[43],"contain":[44],"various":[45],"objects":[46],"numerous":[48],"attributes":[49],"interrelated":[51],"spatial":[52],"relationships.":[53],"While":[54],"many":[55],"regional":[56,92],"prompting":[57,93],"methods":[58],"proposed":[61],"for":[62,94],"UNet-based":[63],"(SD1.5,":[65],"SDXL),":[66],"but":[67],"there":[68],"are":[69],"still":[70],"no":[71],"implementations":[72],"based":[73,96],"on":[74,97],"recent":[76],"Transformer":[78],"(DiT)":[79],"architecture,":[80],"such":[81],"as":[82],"SD3":[83],"FLUX.1.In":[85],"this":[86],"report,":[87],"we":[88],"propose":[89],"implement":[91],"FLUX.1":[95],"attention":[98],"manipulation,":[99],"which":[100],"enables":[101],"DiT":[102],"fined-grained":[104],"compositional":[105],"generation":[107],"capability":[108],"a":[110],"training-free":[111],"manner.":[112],"Code":[113],"is":[114],"available":[115],"at":[116],"https://github.com/antonioo-c/Regional-Prompting-FLUX.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":17}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-11-15T00:00:00"}