{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HFNEBXWBRM37QMIEJD62O52FTA","short_pith_number":"pith:HFNEBXWB","schema_version":"1.0","canonical_sha256":"395a40dec18b37f8310448fda77745981a6a5953eae286b83e37ed61e7b4f076","source":{"kind":"arxiv","id":"2401.04468","version":1},"attestation_state":"computed","paper":{"title":"MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chetwin Low, Daquan Zhou, Hanshu Yan, Jiangqiao Yan, Jiashi Feng, Jiawei Liu, Jie Wu, Jun Hao Liew, Shuo Chen, Tuyen Hoang, Weimin Wang, Zhijie Lin","submitted_at":"2024-01-09T10:12:52Z","abstract_excerpt":"The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika "},"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":"2401.04468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T10:12:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"374f9805455eeaa73992f441cdd4ebb264479accf3e0e03f001e751fed055b58","abstract_canon_sha256":"011e43203b6ffaee297fe547ed925f659e7c70b0df554f1968f3c31702481bee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:44.682132Z","signature_b64":"p3/OqcvCiGZayM0PcGdoV6t2uVDOzL+DR9unTpAxzXaWt/qYStnwXWdVFBq81iUvr+mXoz99pgkPiPwqcBk6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"395a40dec18b37f8310448fda77745981a6a5953eae286b83e37ed61e7b4f076","last_reissued_at":"2026-07-05T07:31:44.681628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:44.681628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chetwin Low, Daquan Zhou, Hanshu Yan, Jiangqiao Yan, Jiashi Feng, Jiawei Liu, Jie Wu, Jun Hao Liew, Shuo Chen, Tuyen Hoang, Weimin Wang, Zhijie Lin","submitted_at":"2024-01-09T10:12:52Z","abstract_excerpt":"The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate an aesthetically pleasing, high-resolution video with remarkable fidelity and smoothness. It demonstrates superior performance over leading Text-to-Video systems such as Runway, Pika "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04468","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/2401.04468/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":"2401.04468","created_at":"2026-07-05T07:31:44.681691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04468v1","created_at":"2026-07-05T07:31:44.681691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04468","created_at":"2026-07-05T07:31:44.681691+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFNEBXWBRM37","created_at":"2026-07-05T07:31:44.681691+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFNEBXWBRM37QMIE","created_at":"2026-07-05T07:31:44.681691+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFNEBXWB","created_at":"2026-07-05T07:31:44.681691+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05961","citing_title":"HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFNEBXWBRM37QMIEJD62O52FTA","json":"https://pith.science/pith/HFNEBXWBRM37QMIEJD62O52FTA.json","graph_json":"https://pith.science/api/pith-number/HFNEBXWBRM37QMIEJD62O52FTA/graph.json","events_json":"https://pith.science/api/pith-number/HFNEBXWBRM37QMIEJD62O52FTA/events.json","paper":"https://pith.science/paper/HFNEBXWB"},"agent_actions":{"view_html":"https://pith.science/pith/HFNEBXWBRM37QMIEJD62O52FTA","download_json":"https://pith.science/pith/HFNEBXWBRM37QMIEJD62O52FTA.json","view_paper":"https://pith.science/paper/HFNEBXWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04468&json=true","fetch_graph":"https://pith.science/api/pith-number/HFNEBXWBRM37QMIEJD62O52FTA/graph.json","fetch_events":"https://pith.science/api/pith-number/HFNEBXWBRM37QMIEJD62O52FTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFNEBXWBRM37QMIEJD62O52FTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFNEBXWBRM37QMIEJD62O52FTA/action/storage_attestation","attest_author":"https://pith.science/pith/HFNEBXWBRM37QMIEJD62O52FTA/action/author_attestation","sign_citation":"https://pith.science/pith/HFNEBXWBRM37QMIEJD62O52FTA/action/citation_signature","submit_replication":"https://pith.science/pith/HFNEBXWBRM37QMIEJD62O52FTA/action/replication_record"}},"created_at":"2026-07-05T07:31:44.681691+00:00","updated_at":"2026-07-05T07:31:44.681691+00:00"}