{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JR34V7LUUCCT2SQGC7K65CWTC3","short_pith_number":"pith:JR34V7LU","schema_version":"1.0","canonical_sha256":"4c77cafd74a0853d4a0617d5ee8ad316c583039159187eb7816224724a73bb74","source":{"kind":"arxiv","id":"2405.12970","version":2},"attestation_state":"computed","paper":{"title":"Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Jiangning Zhang, Junwei Zhu, Keke He, Wei Li, Xiangtai Li, Xu Chen, Yanhao Ge, Yong Liu, Yue Han","submitted_at":"2024-05-21T17:50:12Z","abstract_excerpt":"Current face reenactment and swapping methods mainly rely on GAN frameworks, but recent focus has shifted to pre-trained diffusion models for their superior generation capabilities. However, training these models is resource-intensive, and the results have not yet achieved satisfactory performance levels. To address this issue, we introduce Face-Adapter, an efficient and effective adapter designed for high-precision and high-fidelity face editing for pre-trained diffusion models. We observe that both face reenactment/swapping tasks essentially involve combinations of target structure, ID and a"},"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":"2405.12970","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T17:50:12Z","cross_cats_sorted":[],"title_canon_sha256":"44d754df64272249b925d35f91665a070d5e0047f68370e18a17e16ae0de378e","abstract_canon_sha256":"9874b21e9b6a589f0afee0b7e5fb4a7f2ad8ac9121bb36c366ce4fa66897a7ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:45.337779Z","signature_b64":"fkSU1e5HRX7bEQ3zSN/ipePdOpTua7uwCDeJG7krzLmH1oN6tMo1Y2dZ1ESh+iLk/GtBOgG4Id3+MYH6H+W+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c77cafd74a0853d4a0617d5ee8ad316c583039159187eb7816224724a73bb74","last_reissued_at":"2026-07-05T08:41:45.337290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:45.337290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Jiangning Zhang, Junwei Zhu, Keke He, Wei Li, Xiangtai Li, Xu Chen, Yanhao Ge, Yong Liu, Yue Han","submitted_at":"2024-05-21T17:50:12Z","abstract_excerpt":"Current face reenactment and swapping methods mainly rely on GAN frameworks, but recent focus has shifted to pre-trained diffusion models for their superior generation capabilities. However, training these models is resource-intensive, and the results have not yet achieved satisfactory performance levels. To address this issue, we introduce Face-Adapter, an efficient and effective adapter designed for high-precision and high-fidelity face editing for pre-trained diffusion models. We observe that both face reenactment/swapping tasks essentially involve combinations of target structure, ID and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12970","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/2405.12970/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":"2405.12970","created_at":"2026-07-05T08:41:45.337365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12970v2","created_at":"2026-07-05T08:41:45.337365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12970","created_at":"2026-07-05T08:41:45.337365+00:00"},{"alias_kind":"pith_short_12","alias_value":"JR34V7LUUCCT","created_at":"2026-07-05T08:41:45.337365+00:00"},{"alias_kind":"pith_short_16","alias_value":"JR34V7LUUCCT2SQG","created_at":"2026-07-05T08:41:45.337365+00:00"},{"alias_kind":"pith_short_8","alias_value":"JR34V7LU","created_at":"2026-07-05T08:41:45.337365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.07951","citing_title":"Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JR34V7LUUCCT2SQGC7K65CWTC3","json":"https://pith.science/pith/JR34V7LUUCCT2SQGC7K65CWTC3.json","graph_json":"https://pith.science/api/pith-number/JR34V7LUUCCT2SQGC7K65CWTC3/graph.json","events_json":"https://pith.science/api/pith-number/JR34V7LUUCCT2SQGC7K65CWTC3/events.json","paper":"https://pith.science/paper/JR34V7LU"},"agent_actions":{"view_html":"https://pith.science/pith/JR34V7LUUCCT2SQGC7K65CWTC3","download_json":"https://pith.science/pith/JR34V7LUUCCT2SQGC7K65CWTC3.json","view_paper":"https://pith.science/paper/JR34V7LU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12970&json=true","fetch_graph":"https://pith.science/api/pith-number/JR34V7LUUCCT2SQGC7K65CWTC3/graph.json","fetch_events":"https://pith.science/api/pith-number/JR34V7LUUCCT2SQGC7K65CWTC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JR34V7LUUCCT2SQGC7K65CWTC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JR34V7LUUCCT2SQGC7K65CWTC3/action/storage_attestation","attest_author":"https://pith.science/pith/JR34V7LUUCCT2SQGC7K65CWTC3/action/author_attestation","sign_citation":"https://pith.science/pith/JR34V7LUUCCT2SQGC7K65CWTC3/action/citation_signature","submit_replication":"https://pith.science/pith/JR34V7LUUCCT2SQGC7K65CWTC3/action/replication_record"}},"created_at":"2026-07-05T08:41:45.337365+00:00","updated_at":"2026-07-05T08:41:45.337365+00:00"}