{"id":"https://openalex.org/W4399403247","doi":"https://doi.org/10.48550/arxiv.2406.01561","title":"Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation","display_name":"Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4399403247","doi":"https://doi.org/10.48550/arxiv.2406.01561"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.01561","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.01561","pdf_url":"https://arxiv.org/pdf/2406.01561","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/2406.01561","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010394308","display_name":"Mingyuan Zhou","orcid":"https://orcid.org/0000-0002-4253-2780","observed_orcids":["https://orcid.org/0000-0002-4253-2780"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Mingyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418321","display_name":"Zhendong Wang","orcid":"https://orcid.org/0000-0002-0647-3808","observed_orcids":["https://orcid.org/0000-0002-0647-3808","https://orcid.org/0009-0004-0116-9745"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhendong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077499817","display_name":"Huangjie Zheng","orcid":"https://orcid.org/0000-0003-0508-5034","observed_orcids":["https://orcid.org/0000-0003-0508-5034","https://orcid.org/0009-0004-4910-5679"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Huangjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Huang, Hai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Hai","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":0,"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/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/data-free-knowledge-distillation","display_name":"data-free knowledge distillation","score":0.8069999814033508},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.9160000085830688},{"id":"https://openalex.org/keywords/classifier-free-guidance","display_name":"classifier-free guidance","score":0.7870000004768372},{"id":"https://openalex.org/keywords/score-matching","display_name":"score matching","score":0.6650000214576721},{"id":"https://openalex.org/keywords/stable-diffusion","display_name":"Stable Diffusion","score":0.8980000019073486},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8159999847412109},{"id":"https://openalex.org/keywords/synthetic-training-data","display_name":"synthetic training data","score":0.6140000224113464},{"id":"https://openalex.org/keywords/image-quality-assessment","display_name":"image quality assessment","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6713950037956238},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6230353713035583},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5311635136604309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43129363656044006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43049079179763794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3888043165206909},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.2642682194709778},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.1570957899093628},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.14446350932121277},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11966487765312195}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.01561","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.01561","pdf_url":"https://arxiv.org/pdf/2406.01561","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.2406.01561","doi":"https://doi.org/10.48550/arxiv.2406.01561","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.01561","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:2406.01561","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.01561","pdf_url":"https://arxiv.org/pdf/2406.01561","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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417302166","https://openalex.org/W4402727382","https://openalex.org/W4394591914","https://openalex.org/W7221946134","https://openalex.org/W4386722101","https://openalex.org/W4409347087","https://openalex.org/W4413147532","https://openalex.org/W4404346261","https://openalex.org/W4415797645","https://openalex.org/W4417453513"],"abstract_inverted_index":{"Diffusion-based":[0],"text-to-image":[1],"generation":[2,32],"models":[3,27,61],"trained":[4],"on":[5,186],"extensive":[6],"text-image":[7],"pairs":[8],"have":[9],"demonstrated":[10],"the":[11,39,54,65,103,106,113,118,174,187,196],"ability":[12],"to":[13,64,72,102,112],"produce":[14],"photorealistic":[15],"images":[16,147],"aligned":[17],"with":[18,85,145],"textual":[19],"descriptions.":[20],"However,":[21],"a":[22,47,124,131,169,191],"significant":[23],"limitation":[24],"of":[25,57,105,117,177,184],"these":[26],"is":[28],"their":[29],"slow":[30],"sample":[31],"process,":[33],"which":[34],"requires":[35],"iterative":[36],"refinement":[37],"through":[38],"same":[40],"network.":[41,121],"To":[42],"overcome":[43],"this,":[44],"we":[45],"introduce":[46],"data-free":[48,154,197],"guided":[49],"distillation":[50,56,155,176],"method":[51,79,156],"that":[52,95],"enables":[53],"efficient":[55],"pretrained":[58,107],"Stable":[59,178],"Diffusion":[60,179],"without":[62],"access":[63],"real":[66],"training":[67,114,144],"data,":[68],"often":[69],"restricted":[70],"due":[71],"legal,":[73],"privacy,":[74],"or":[75],"cost":[76],"concerns.":[77],"This":[78],"enhances":[80],"Score":[81],"identity":[82],"Distillation":[83],"(SiD)":[84],"Long":[86],"and":[87,115,160,201],"Short":[88],"Classifier-Free":[89,97],"Guidance":[90,98],"(LSG),":[91],"an":[92,182],"innovative":[93],"strategy":[94],"applies":[96],"(CFG)":[99],"not":[100],"only":[101],"evaluation":[104,116],"diffusion":[108],"model":[109],"but":[110],"also":[111],"fake":[119],"score":[120,127],"We":[122],"optimize":[123],"model-based":[125],"explicit":[126],"matching":[128],"loss":[129],"using":[130],"score-identity-based":[132],"approximation":[133],"alongside":[134],"our":[135,153],"proposed":[136],"guidance":[137],"strategies":[138],"for":[139],"practical":[140],"computation.":[141],"By":[142],"exclusively":[143],"synthetic":[146],"generated":[148],"by":[149],"its":[150],"one-step":[151,175],"generator,":[152],"rapidly":[157],"improves":[158],"FID":[159,165,183],"CLIP":[161,171],"scores,":[162],"achieving":[163],"state-of-the-art":[164],"performance":[166],"while":[167],"maintaining":[168],"competitive":[170],"score.":[172],"Notably,":[173],"1.5":[180],"achieves":[181],"8.15":[185],"COCO-2014":[188],"validation":[189],"set,":[190],"record":[192],"low":[193],"value":[194],"under":[195],"setting.":[198],"Our":[199],"code":[200],"checkpoints":[202],"are":[203],"available":[204],"at":[205],"https://github.com/mingyuanzhou/SiD-LSG.":[206]},"counts_by_year":[],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2024-06-07T00:00:00"}