{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3OTXX5GAES5ZAXD7IP7QPPHWWN","short_pith_number":"pith:3OTXX5GA","schema_version":"1.0","canonical_sha256":"dba77bf4c024bb905c7f43ff07bcf6b3506b206984908c2594a9586719b8db93","source":{"kind":"arxiv","id":"2306.00926","version":1},"attestation_state":"computed","paper":{"title":"Inserting Anybody in Diffusion Models via Celeb Basis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Qi, Ge Yuan, Huicheng Zheng, Maomao Li, Xiaodong Cun, Xintao Wang, Ying Shan, Yong Zhang","submitted_at":"2023-06-01T17:30:24Z","abstract_excerpt":"Exquisite demand exists for customizing the pretrained large text-to-image model, $\\textit{e.g.}$, Stable Diffusion, to generate innovative concepts, such as the users themselves. However, the newly-added concept from previous customization methods often shows weaker combination abilities than the original ones even given several images during training. We thus propose a new personalization method that allows for the seamless integration of a unique individual into the pre-trained diffusion model using just $\\textbf{one facial photograph}$ and only $\\textbf{1024 learnable parameters}$ under $\\"},"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":"2306.00926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T17:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"5634a1401c1f1f9f47eb65a821df295cab813754f0c284bec22665309e550e6c","abstract_canon_sha256":"b7d04da77086d999e77aa7d9971bced66247fc6a5f5ed0600ef3e2d0c9e37f60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:33.393830Z","signature_b64":"GfmVR+dGl8854lN3/sDVbCiPxqoTC/QbBO6/GMU79cwH2a8t8ClX0NgpTzeEO46gudWdkBUPkqOX7Q348NsOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dba77bf4c024bb905c7f43ff07bcf6b3506b206984908c2594a9586719b8db93","last_reissued_at":"2026-07-05T06:16:33.393370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:33.393370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inserting Anybody in Diffusion Models via Celeb Basis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Qi, Ge Yuan, Huicheng Zheng, Maomao Li, Xiaodong Cun, Xintao Wang, Ying Shan, Yong Zhang","submitted_at":"2023-06-01T17:30:24Z","abstract_excerpt":"Exquisite demand exists for customizing the pretrained large text-to-image model, $\\textit{e.g.}$, Stable Diffusion, to generate innovative concepts, such as the users themselves. However, the newly-added concept from previous customization methods often shows weaker combination abilities than the original ones even given several images during training. We thus propose a new personalization method that allows for the seamless integration of a unique individual into the pre-trained diffusion model using just $\\textbf{one facial photograph}$ and only $\\textbf{1024 learnable parameters}$ under $\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00926","kind":"arxiv","version":1},"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/2306.00926/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":"2306.00926","created_at":"2026-07-05T06:16:33.393423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00926v1","created_at":"2026-07-05T06:16:33.393423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00926","created_at":"2026-07-05T06:16:33.393423+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OTXX5GAES5Z","created_at":"2026-07-05T06:16:33.393423+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OTXX5GAES5ZAXD7","created_at":"2026-07-05T06:16:33.393423+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OTXX5GA","created_at":"2026-07-05T06:16:33.393423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30894","citing_title":"SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13863","citing_title":"PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OTXX5GAES5ZAXD7IP7QPPHWWN","json":"https://pith.science/pith/3OTXX5GAES5ZAXD7IP7QPPHWWN.json","graph_json":"https://pith.science/api/pith-number/3OTXX5GAES5ZAXD7IP7QPPHWWN/graph.json","events_json":"https://pith.science/api/pith-number/3OTXX5GAES5ZAXD7IP7QPPHWWN/events.json","paper":"https://pith.science/paper/3OTXX5GA"},"agent_actions":{"view_html":"https://pith.science/pith/3OTXX5GAES5ZAXD7IP7QPPHWWN","download_json":"https://pith.science/pith/3OTXX5GAES5ZAXD7IP7QPPHWWN.json","view_paper":"https://pith.science/paper/3OTXX5GA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00926&json=true","fetch_graph":"https://pith.science/api/pith-number/3OTXX5GAES5ZAXD7IP7QPPHWWN/graph.json","fetch_events":"https://pith.science/api/pith-number/3OTXX5GAES5ZAXD7IP7QPPHWWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OTXX5GAES5ZAXD7IP7QPPHWWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OTXX5GAES5ZAXD7IP7QPPHWWN/action/storage_attestation","attest_author":"https://pith.science/pith/3OTXX5GAES5ZAXD7IP7QPPHWWN/action/author_attestation","sign_citation":"https://pith.science/pith/3OTXX5GAES5ZAXD7IP7QPPHWWN/action/citation_signature","submit_replication":"https://pith.science/pith/3OTXX5GAES5ZAXD7IP7QPPHWWN/action/replication_record"}},"created_at":"2026-07-05T06:16:33.393423+00:00","updated_at":"2026-07-05T06:16:33.393423+00:00"}