{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DGLEX3AKATCJSASBIOHJBHTD4R","short_pith_number":"pith:DGLEX3AK","schema_version":"1.0","canonical_sha256":"19964bec0a04c4990241438e909e63e46d84bee06beba97d9046149445b4ea73","source":{"kind":"arxiv","id":"2306.00971","version":2},"attestation_state":"computed","paper":{"title":"ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kai Han, Kwan-Yee K. Wong, Shaozhe Hao, Shihao Zhao","submitted_at":"2023-06-01T17:58:44Z","abstract_excerpt":"Personalized text-to-image generation using diffusion models has recently emerged and garnered significant interest. This task learns a novel concept (e.g., a unique toy), illustrated in a handful of images, into a generative model that captures fine visual details and generates photorealistic images based on textual embeddings. In this paper, we present ViCo, a novel lightweight plug-and-play method that seamlessly integrates visual condition into personalized text-to-image generation. ViCo stands out for its unique feature of not requiring any fine-tuning of the original diffusion model para"},"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":"2306.00971","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T17:58:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3781801244a589248a79e8a3c86799ee3376fa23b9fafd0c604aebef254252bc","abstract_canon_sha256":"66245421a5e67a50f6c6eb621d331210d05ead979c8c9b8f0e3265287bb33a8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:26.721551Z","signature_b64":"oZCniw0vGNPoWhc719yMEEbV3S5llHx86Ek81D7fPfxppspleYNN556gBbgr2QghhxF/4QWggFi5/amDNARoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19964bec0a04c4990241438e909e63e46d84bee06beba97d9046149445b4ea73","last_reissued_at":"2026-07-05T07:21:26.721079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:26.721079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kai Han, Kwan-Yee K. Wong, Shaozhe Hao, Shihao Zhao","submitted_at":"2023-06-01T17:58:44Z","abstract_excerpt":"Personalized text-to-image generation using diffusion models has recently emerged and garnered significant interest. This task learns a novel concept (e.g., a unique toy), illustrated in a handful of images, into a generative model that captures fine visual details and generates photorealistic images based on textual embeddings. In this paper, we present ViCo, a novel lightweight plug-and-play method that seamlessly integrates visual condition into personalized text-to-image generation. ViCo stands out for its unique feature of not requiring any fine-tuning of the original diffusion model para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00971","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/2306.00971/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":"2306.00971","created_at":"2026-07-05T07:21:26.721134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00971v2","created_at":"2026-07-05T07:21:26.721134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00971","created_at":"2026-07-05T07:21:26.721134+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGLEX3AKATCJ","created_at":"2026-07-05T07:21:26.721134+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGLEX3AKATCJSASB","created_at":"2026-07-05T07:21:26.721134+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGLEX3AK","created_at":"2026-07-05T07:21:26.721134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20237","citing_title":"AnimeAdapter: A Modular Adapter for Appearance-Consistent Anime Character Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08090","citing_title":"DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11795","citing_title":"Intrinsic Concept Extraction Based on Compositional Interpretability","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGLEX3AKATCJSASBIOHJBHTD4R","json":"https://pith.science/pith/DGLEX3AKATCJSASBIOHJBHTD4R.json","graph_json":"https://pith.science/api/pith-number/DGLEX3AKATCJSASBIOHJBHTD4R/graph.json","events_json":"https://pith.science/api/pith-number/DGLEX3AKATCJSASBIOHJBHTD4R/events.json","paper":"https://pith.science/paper/DGLEX3AK"},"agent_actions":{"view_html":"https://pith.science/pith/DGLEX3AKATCJSASBIOHJBHTD4R","download_json":"https://pith.science/pith/DGLEX3AKATCJSASBIOHJBHTD4R.json","view_paper":"https://pith.science/paper/DGLEX3AK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00971&json=true","fetch_graph":"https://pith.science/api/pith-number/DGLEX3AKATCJSASBIOHJBHTD4R/graph.json","fetch_events":"https://pith.science/api/pith-number/DGLEX3AKATCJSASBIOHJBHTD4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGLEX3AKATCJSASBIOHJBHTD4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGLEX3AKATCJSASBIOHJBHTD4R/action/storage_attestation","attest_author":"https://pith.science/pith/DGLEX3AKATCJSASBIOHJBHTD4R/action/author_attestation","sign_citation":"https://pith.science/pith/DGLEX3AKATCJSASBIOHJBHTD4R/action/citation_signature","submit_replication":"https://pith.science/pith/DGLEX3AKATCJSASBIOHJBHTD4R/action/replication_record"}},"created_at":"2026-07-05T07:21:26.721134+00:00","updated_at":"2026-07-05T07:21:26.721134+00:00"}