{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U2VKCK2AZZTKYHCQ6KGSW5ID63","short_pith_number":"pith:U2VKCK2A","schema_version":"1.0","canonical_sha256":"a6aaa12b40ce66ac1c50f28d2b7503f6c813d0795972a25c946f1147e300166a","source":{"kind":"arxiv","id":"2412.13479","version":1},"attestation_state":"computed","paper":{"title":"Real-time One-Step Diffusion-based Expressive Portrait Videos Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander William Bergman, Daquan Zhou, Hanzhong Guo, Hongwei Yi, Michael Lingelbach, Yizhou Yu","submitted_at":"2024-12-18T03:42:42Z","abstract_excerpt":"Latent diffusion models have made great strides in generating expressive portrait videos with accurate lip-sync and natural motion from a single reference image and audio input. However, these models are far from real-time, often requiring many sampling steps that take minutes to generate even one second of video-significantly limiting practical use. We introduce OSA-LCM (One-Step Avatar Latent Consistency Model), paving the way for real-time diffusion-based avatars. Our method achieves comparable video quality to existing methods but requires only one sampling step, making it more than 10x fa"},"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":"2412.13479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T03:42:42Z","cross_cats_sorted":[],"title_canon_sha256":"c7523a0edfe5d6264f751a80b53a55d56020870ff736e19fb545041202f67b2d","abstract_canon_sha256":"876030a224820a7fcd2b9d9ad0875f822bba11b1c4c7abde9274cc532e5e81b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:02.498229Z","signature_b64":"/H6ue22FqcbYbJzE39UhqHuyVRGDDNiPenIHElZ5rnQebyjaqz0oRpMUFbh7NPFSZXOR8702gzNwLf1gkxxkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6aaa12b40ce66ac1c50f28d2b7503f6c813d0795972a25c946f1147e300166a","last_reissued_at":"2026-07-05T09:51:02.497763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:02.497763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-time One-Step Diffusion-based Expressive Portrait Videos Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander William Bergman, Daquan Zhou, Hanzhong Guo, Hongwei Yi, Michael Lingelbach, Yizhou Yu","submitted_at":"2024-12-18T03:42:42Z","abstract_excerpt":"Latent diffusion models have made great strides in generating expressive portrait videos with accurate lip-sync and natural motion from a single reference image and audio input. However, these models are far from real-time, often requiring many sampling steps that take minutes to generate even one second of video-significantly limiting practical use. We introduce OSA-LCM (One-Step Avatar Latent Consistency Model), paving the way for real-time diffusion-based avatars. Our method achieves comparable video quality to existing methods but requires only one sampling step, making it more than 10x fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13479","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/2412.13479/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":"2412.13479","created_at":"2026-07-05T09:51:02.497814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13479v1","created_at":"2026-07-05T09:51:02.497814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13479","created_at":"2026-07-05T09:51:02.497814+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2VKCK2AZZTK","created_at":"2026-07-05T09:51:02.497814+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2VKCK2AZZTKYHCQ","created_at":"2026-07-05T09:51:02.497814+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2VKCK2A","created_at":"2026-07-05T09:51:02.497814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20807","citing_title":"Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":239,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":282,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U2VKCK2AZZTKYHCQ6KGSW5ID63","json":"https://pith.science/pith/U2VKCK2AZZTKYHCQ6KGSW5ID63.json","graph_json":"https://pith.science/api/pith-number/U2VKCK2AZZTKYHCQ6KGSW5ID63/graph.json","events_json":"https://pith.science/api/pith-number/U2VKCK2AZZTKYHCQ6KGSW5ID63/events.json","paper":"https://pith.science/paper/U2VKCK2A"},"agent_actions":{"view_html":"https://pith.science/pith/U2VKCK2AZZTKYHCQ6KGSW5ID63","download_json":"https://pith.science/pith/U2VKCK2AZZTKYHCQ6KGSW5ID63.json","view_paper":"https://pith.science/paper/U2VKCK2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13479&json=true","fetch_graph":"https://pith.science/api/pith-number/U2VKCK2AZZTKYHCQ6KGSW5ID63/graph.json","fetch_events":"https://pith.science/api/pith-number/U2VKCK2AZZTKYHCQ6KGSW5ID63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2VKCK2AZZTKYHCQ6KGSW5ID63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2VKCK2AZZTKYHCQ6KGSW5ID63/action/storage_attestation","attest_author":"https://pith.science/pith/U2VKCK2AZZTKYHCQ6KGSW5ID63/action/author_attestation","sign_citation":"https://pith.science/pith/U2VKCK2AZZTKYHCQ6KGSW5ID63/action/citation_signature","submit_replication":"https://pith.science/pith/U2VKCK2AZZTKYHCQ6KGSW5ID63/action/replication_record"}},"created_at":"2026-07-05T09:51:02.497814+00:00","updated_at":"2026-07-05T09:51:02.497814+00:00"}