{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H3CFHTFYLS545LSRVD7HYM4FCI","short_pith_number":"pith:H3CFHTFY","schema_version":"1.0","canonical_sha256":"3ec453ccb85cbbceae51a8fe7c3385120615441667bbb1baf90b65b0170dee48","source":{"kind":"arxiv","id":"2402.12974","version":2},"attestation_state":"computed","paper":{"title":"Visual Style Prompting with Swapping Self-Attention","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gayoung Lee, Jaeseok Jeong, Junho Kim, Youngjung Uh, Yunjey Choi","submitted_at":"2024-02-20T12:51:17Z","abstract_excerpt":"In the evolving domain of text-to-image generation, diffusion models have emerged as powerful tools in content creation. Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a consistent style, requiring costly fine-tuning or often inadequately transferring the visual elements due to content leakage. To address these challenges, we propose a novel approach, \\ours, to produce a diverse range of images while maintaining specific style elements and nuances. During the denoising process, we keep the query from original features while sw"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.12974","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T12:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"dddb28f1060d9eb353c305ce832ac03c07a8c652d3075d93833b55fe8af071b6","abstract_canon_sha256":"6cb0d63d1d3ea0d56313459c5b45be13bf404002497973d2ee065ae69c886345"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:47.125136Z","signature_b64":"L4p480j0JYPjwczbY1SgN6fgr7OAiDNptPvOBw7wQEpC6OCmYaTSzSC23wBTFeaOEsbg88loq6GzzVpDlwuXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ec453ccb85cbbceae51a8fe7c3385120615441667bbb1baf90b65b0170dee48","last_reissued_at":"2026-07-05T07:47:47.124547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:47.124547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Style Prompting with Swapping Self-Attention","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gayoung Lee, Jaeseok Jeong, Junho Kim, Youngjung Uh, Yunjey Choi","submitted_at":"2024-02-20T12:51:17Z","abstract_excerpt":"In the evolving domain of text-to-image generation, diffusion models have emerged as powerful tools in content creation. Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a consistent style, requiring costly fine-tuning or often inadequately transferring the visual elements due to content leakage. To address these challenges, we propose a novel approach, \\ours, to produce a diverse range of images while maintaining specific style elements and nuances. During the denoising process, we keep the query from original features while sw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12974","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.12974/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.12974","created_at":"2026-07-05T07:47:47.124622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12974v2","created_at":"2026-07-05T07:47:47.124622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12974","created_at":"2026-07-05T07:47:47.124622+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3CFHTFYLS54","created_at":"2026-07-05T07:47:47.124622+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3CFHTFYLS545LSR","created_at":"2026-07-05T07:47:47.124622+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3CFHTFY","created_at":"2026-07-05T07:47:47.124622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26668","citing_title":"Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20506","citing_title":"FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14842","citing_title":"Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2412.12242","citing_title":"OmniPrism: Learning Disentangled Visual Concept for Image Generation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3CFHTFYLS545LSRVD7HYM4FCI","json":"https://pith.science/pith/H3CFHTFYLS545LSRVD7HYM4FCI.json","graph_json":"https://pith.science/api/pith-number/H3CFHTFYLS545LSRVD7HYM4FCI/graph.json","events_json":"https://pith.science/api/pith-number/H3CFHTFYLS545LSRVD7HYM4FCI/events.json","paper":"https://pith.science/paper/H3CFHTFY"},"agent_actions":{"view_html":"https://pith.science/pith/H3CFHTFYLS545LSRVD7HYM4FCI","download_json":"https://pith.science/pith/H3CFHTFYLS545LSRVD7HYM4FCI.json","view_paper":"https://pith.science/paper/H3CFHTFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12974&json=true","fetch_graph":"https://pith.science/api/pith-number/H3CFHTFYLS545LSRVD7HYM4FCI/graph.json","fetch_events":"https://pith.science/api/pith-number/H3CFHTFYLS545LSRVD7HYM4FCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3CFHTFYLS545LSRVD7HYM4FCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3CFHTFYLS545LSRVD7HYM4FCI/action/storage_attestation","attest_author":"https://pith.science/pith/H3CFHTFYLS545LSRVD7HYM4FCI/action/author_attestation","sign_citation":"https://pith.science/pith/H3CFHTFYLS545LSRVD7HYM4FCI/action/citation_signature","submit_replication":"https://pith.science/pith/H3CFHTFYLS545LSRVD7HYM4FCI/action/replication_record"}},"created_at":"2026-07-05T07:47:47.124622+00:00","updated_at":"2026-07-05T07:47:47.124622+00:00"}