{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2P4VW46CMNFZIDGIDMZ66ETSPT","short_pith_number":"pith:2P4VW46C","schema_version":"1.0","canonical_sha256":"d3f95b73c2634b940cc81b33ef12727cf8a165acbe41dda0b8533a78502675b7","source":{"kind":"arxiv","id":"2410.07763","version":1},"attestation_state":"computed","paper":{"title":"HARIVO: Harnessing Text-to-Image Models for Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baqiao Liu, Difan Liu, Feng Liu, Haoran Cai, Joon-Young Lee, Mingi Kwon, Seoung Wug Oh, Yang Zhou, Youngjung Uh","submitted_at":"2024-10-10T09:47:39Z","abstract_excerpt":"We present a method to create diffusion-based video models from pretrained Text-to-Image (T2I) models. Recently, AnimateDiff proposed freezing the T2I model while only training temporal layers. We advance this method by proposing a unique architecture, incorporating a mapping network and frame-wise tokens, tailored for video generation while maintaining the diversity and creativity of the original T2I model. Key innovations include novel loss functions for temporal smoothness and a mitigating gradient sampling technique, ensuring realistic and temporally consistent video generation despite lim"},"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":"2410.07763","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T09:47:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99465775f526361e4e980a72ffba1a4fe1b09b58a0f51a1b5a9bb1f8dbe46932","abstract_canon_sha256":"26c69d98b8a00f6b008c6f58f50adb6ba1898a50fe4da82e3344f0a41d5820ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:43.447517Z","signature_b64":"n9jAgPP6E/uhBaGqwo1FkER0wPs7mei8dtzM0StHJwGrcCOtzCnSgg7ujzG7WSZRfNWFG8o/oZLlG60Xll1NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3f95b73c2634b940cc81b33ef12727cf8a165acbe41dda0b8533a78502675b7","last_reissued_at":"2026-07-05T09:18:43.447092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:43.447092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HARIVO: Harnessing Text-to-Image Models for Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baqiao Liu, Difan Liu, Feng Liu, Haoran Cai, Joon-Young Lee, Mingi Kwon, Seoung Wug Oh, Yang Zhou, Youngjung Uh","submitted_at":"2024-10-10T09:47:39Z","abstract_excerpt":"We present a method to create diffusion-based video models from pretrained Text-to-Image (T2I) models. Recently, AnimateDiff proposed freezing the T2I model while only training temporal layers. We advance this method by proposing a unique architecture, incorporating a mapping network and frame-wise tokens, tailored for video generation while maintaining the diversity and creativity of the original T2I model. Key innovations include novel loss functions for temporal smoothness and a mitigating gradient sampling technique, ensuring realistic and temporally consistent video generation despite lim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07763","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/2410.07763/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":"2410.07763","created_at":"2026-07-05T09:18:43.447144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07763v1","created_at":"2026-07-05T09:18:43.447144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07763","created_at":"2026-07-05T09:18:43.447144+00:00"},{"alias_kind":"pith_short_12","alias_value":"2P4VW46CMNFZ","created_at":"2026-07-05T09:18:43.447144+00:00"},{"alias_kind":"pith_short_16","alias_value":"2P4VW46CMNFZIDGI","created_at":"2026-07-05T09:18:43.447144+00:00"},{"alias_kind":"pith_short_8","alias_value":"2P4VW46C","created_at":"2026-07-05T09:18:43.447144+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/2P4VW46CMNFZIDGIDMZ66ETSPT","json":"https://pith.science/pith/2P4VW46CMNFZIDGIDMZ66ETSPT.json","graph_json":"https://pith.science/api/pith-number/2P4VW46CMNFZIDGIDMZ66ETSPT/graph.json","events_json":"https://pith.science/api/pith-number/2P4VW46CMNFZIDGIDMZ66ETSPT/events.json","paper":"https://pith.science/paper/2P4VW46C"},"agent_actions":{"view_html":"https://pith.science/pith/2P4VW46CMNFZIDGIDMZ66ETSPT","download_json":"https://pith.science/pith/2P4VW46CMNFZIDGIDMZ66ETSPT.json","view_paper":"https://pith.science/paper/2P4VW46C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07763&json=true","fetch_graph":"https://pith.science/api/pith-number/2P4VW46CMNFZIDGIDMZ66ETSPT/graph.json","fetch_events":"https://pith.science/api/pith-number/2P4VW46CMNFZIDGIDMZ66ETSPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2P4VW46CMNFZIDGIDMZ66ETSPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2P4VW46CMNFZIDGIDMZ66ETSPT/action/storage_attestation","attest_author":"https://pith.science/pith/2P4VW46CMNFZIDGIDMZ66ETSPT/action/author_attestation","sign_citation":"https://pith.science/pith/2P4VW46CMNFZIDGIDMZ66ETSPT/action/citation_signature","submit_replication":"https://pith.science/pith/2P4VW46CMNFZIDGIDMZ66ETSPT/action/replication_record"}},"created_at":"2026-07-05T09:18:43.447144+00:00","updated_at":"2026-07-05T09:18:43.447144+00:00"}