{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VNG3WKAWMMEZZEK4OYOXTN7JNU","short_pith_number":"pith:VNG3WKAW","schema_version":"1.0","canonical_sha256":"ab4dbb281663099c915c761d79b7e96d248351c634af422ce0cb444b914bae7d","source":{"kind":"arxiv","id":"2605.30230","version":1},"attestation_state":"computed","paper":{"title":"IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wang, Hao Wu, Jiawei Zhang, Jinwei Wang, Xiangyang Luo, Yi Zhang","submitted_at":"2026-05-28T17:00:37Z","abstract_excerpt":"With the rapid advancement of diffusion models, talking face generation has made remarkable progress. However, existing diffusion-based methods still require task-specific fine-tuning and large-scale audiovisual datasets, resulting in high computational costs that hinder scalability and accessibility of diffusion-based approaches across the research community. To address this, we propose a finetuning-free paradigm that directly performs talking face generation using the pretrained weights of Stable Diffusion and IP-Adapter. This backbone leverages the visual embedding capability of IP-Adapter "},"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":"2605.30230","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:00:37Z","cross_cats_sorted":[],"title_canon_sha256":"e5bd8d8c68a2f365454e53f7490ec2c2a6e49b7d3fb2c311262e3e201cb186d5","abstract_canon_sha256":"5dffc24cc1a161369e35815338bb356de99f165f0e4df15fd76b3ca5c87973e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:13.452956Z","signature_b64":"l2VMN8OPIuR6uQNrXxC7Q14Vn0lQ5LSs0D5KVhGIsZBWL44c1czakWZstqrmK/EyQFUvhSI9PN7ZrmdRHloSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab4dbb281663099c915c761d79b7e96d248351c634af422ce0cb444b914bae7d","last_reissued_at":"2026-05-29T02:06:13.452610Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:13.452610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wang, Hao Wu, Jiawei Zhang, Jinwei Wang, Xiangyang Luo, Yi Zhang","submitted_at":"2026-05-28T17:00:37Z","abstract_excerpt":"With the rapid advancement of diffusion models, talking face generation has made remarkable progress. However, existing diffusion-based methods still require task-specific fine-tuning and large-scale audiovisual datasets, resulting in high computational costs that hinder scalability and accessibility of diffusion-based approaches across the research community. To address this, we propose a finetuning-free paradigm that directly performs talking face generation using the pretrained weights of Stable Diffusion and IP-Adapter. This backbone leverages the visual embedding capability of IP-Adapter "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30230","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/2605.30230/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":"2605.30230","created_at":"2026-05-29T02:06:13.452672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30230v1","created_at":"2026-05-29T02:06:13.452672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30230","created_at":"2026-05-29T02:06:13.452672+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNG3WKAWMMEZ","created_at":"2026-05-29T02:06:13.452672+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNG3WKAWMMEZZEK4","created_at":"2026-05-29T02:06:13.452672+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNG3WKAW","created_at":"2026-05-29T02:06:13.452672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNG3WKAWMMEZZEK4OYOXTN7JNU","json":"https://pith.science/pith/VNG3WKAWMMEZZEK4OYOXTN7JNU.json","graph_json":"https://pith.science/api/pith-number/VNG3WKAWMMEZZEK4OYOXTN7JNU/graph.json","events_json":"https://pith.science/api/pith-number/VNG3WKAWMMEZZEK4OYOXTN7JNU/events.json","paper":"https://pith.science/paper/VNG3WKAW"},"agent_actions":{"view_html":"https://pith.science/pith/VNG3WKAWMMEZZEK4OYOXTN7JNU","download_json":"https://pith.science/pith/VNG3WKAWMMEZZEK4OYOXTN7JNU.json","view_paper":"https://pith.science/paper/VNG3WKAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30230&json=true","fetch_graph":"https://pith.science/api/pith-number/VNG3WKAWMMEZZEK4OYOXTN7JNU/graph.json","fetch_events":"https://pith.science/api/pith-number/VNG3WKAWMMEZZEK4OYOXTN7JNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNG3WKAWMMEZZEK4OYOXTN7JNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNG3WKAWMMEZZEK4OYOXTN7JNU/action/storage_attestation","attest_author":"https://pith.science/pith/VNG3WKAWMMEZZEK4OYOXTN7JNU/action/author_attestation","sign_citation":"https://pith.science/pith/VNG3WKAWMMEZZEK4OYOXTN7JNU/action/citation_signature","submit_replication":"https://pith.science/pith/VNG3WKAWMMEZZEK4OYOXTN7JNU/action/replication_record"}},"created_at":"2026-05-29T02:06:13.452672+00:00","updated_at":"2026-05-29T02:06:13.452672+00:00"}