{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HL4OG7MMEUHQA7QW3CDCGTW7NL","short_pith_number":"pith:HL4OG7MM","schema_version":"1.0","canonical_sha256":"3af8e37d8c250f007e16d886234edf6afc93b5622a6cafd992362aba1575e4f9","source":{"kind":"arxiv","id":"2403.05438","version":1},"attestation_state":"computed","paper":{"title":"VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peiran Ren, Wangmeng Zuo, Xiangyang Ji, Xianhui Lin, Xuansong Xie, Yabo Zhang, Yuxiang Wei, Zheng Hui","submitted_at":"2024-03-08T16:44:54Z","abstract_excerpt":"Text-to-image diffusion models (T2I) have demonstrated unprecedented capabilities in creating realistic and aesthetic images. On the contrary, text-to-video diffusion models (T2V) still lag far behind in frame quality and text alignment, owing to insufficient quality and quantity of training videos. In this paper, we introduce VideoElevator, a training-free and plug-and-play method, which elevates the performance of T2V using superior capabilities of T2I. Different from conventional T2V sampling (i.e., temporal and spatial modeling), VideoElevator explicitly decomposes each sampling step into "},"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":"2403.05438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T16:44:54Z","cross_cats_sorted":[],"title_canon_sha256":"85abaf74c85fe86b68e8726ea7c4d3f6b46791e18fcac7db3978e6d4c6871273","abstract_canon_sha256":"42faff0466a8ae344107cb0b510f2c4a5241ce0d7e5755b58b3c545b8551712d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:55.140936Z","signature_b64":"CiYWaAY7uv3TvouFYqVc6X59lsymUbvKoTpTtQuxhFbpr4NKckVqJDV2SMgDfpNqTCDwkhxyXvfQkDlvVvVMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3af8e37d8c250f007e16d886234edf6afc93b5622a6cafd992362aba1575e4f9","last_reissued_at":"2026-07-05T07:53:55.140442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:55.140442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peiran Ren, Wangmeng Zuo, Xiangyang Ji, Xianhui Lin, Xuansong Xie, Yabo Zhang, Yuxiang Wei, Zheng Hui","submitted_at":"2024-03-08T16:44:54Z","abstract_excerpt":"Text-to-image diffusion models (T2I) have demonstrated unprecedented capabilities in creating realistic and aesthetic images. On the contrary, text-to-video diffusion models (T2V) still lag far behind in frame quality and text alignment, owing to insufficient quality and quantity of training videos. In this paper, we introduce VideoElevator, a training-free and plug-and-play method, which elevates the performance of T2V using superior capabilities of T2I. Different from conventional T2V sampling (i.e., temporal and spatial modeling), VideoElevator explicitly decomposes each sampling step into "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05438","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/2403.05438/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":"2403.05438","created_at":"2026-07-05T07:53:55.140502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05438v1","created_at":"2026-07-05T07:53:55.140502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05438","created_at":"2026-07-05T07:53:55.140502+00:00"},{"alias_kind":"pith_short_12","alias_value":"HL4OG7MMEUHQ","created_at":"2026-07-05T07:53:55.140502+00:00"},{"alias_kind":"pith_short_16","alias_value":"HL4OG7MMEUHQA7QW","created_at":"2026-07-05T07:53:55.140502+00:00"},{"alias_kind":"pith_short_8","alias_value":"HL4OG7MM","created_at":"2026-07-05T07:53:55.140502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13753","citing_title":"Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HL4OG7MMEUHQA7QW3CDCGTW7NL","json":"https://pith.science/pith/HL4OG7MMEUHQA7QW3CDCGTW7NL.json","graph_json":"https://pith.science/api/pith-number/HL4OG7MMEUHQA7QW3CDCGTW7NL/graph.json","events_json":"https://pith.science/api/pith-number/HL4OG7MMEUHQA7QW3CDCGTW7NL/events.json","paper":"https://pith.science/paper/HL4OG7MM"},"agent_actions":{"view_html":"https://pith.science/pith/HL4OG7MMEUHQA7QW3CDCGTW7NL","download_json":"https://pith.science/pith/HL4OG7MMEUHQA7QW3CDCGTW7NL.json","view_paper":"https://pith.science/paper/HL4OG7MM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05438&json=true","fetch_graph":"https://pith.science/api/pith-number/HL4OG7MMEUHQA7QW3CDCGTW7NL/graph.json","fetch_events":"https://pith.science/api/pith-number/HL4OG7MMEUHQA7QW3CDCGTW7NL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HL4OG7MMEUHQA7QW3CDCGTW7NL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HL4OG7MMEUHQA7QW3CDCGTW7NL/action/storage_attestation","attest_author":"https://pith.science/pith/HL4OG7MMEUHQA7QW3CDCGTW7NL/action/author_attestation","sign_citation":"https://pith.science/pith/HL4OG7MMEUHQA7QW3CDCGTW7NL/action/citation_signature","submit_replication":"https://pith.science/pith/HL4OG7MMEUHQA7QW3CDCGTW7NL/action/replication_record"}},"created_at":"2026-07-05T07:53:55.140502+00:00","updated_at":"2026-07-05T07:53:55.140502+00:00"}