{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:23KHMHMDVZXKJXV44YTB3OR4GP","short_pith_number":"pith:23KHMHMD","schema_version":"1.0","canonical_sha256":"d6d4761d83ae6ea4debce6261dba3c33d9a20555cdefd759699610eced734f47","source":{"kind":"arxiv","id":"2312.07537","version":2},"attestation_state":"computed","paper":{"title":"FreeInit: Bridging Initialization Gap in Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Si, Tianxing Wu, Yuming Jiang, Ziqi Huang, Ziwei Liu","submitted_at":"2023-12-12T18:59:16Z","abstract_excerpt":"Though diffusion-based video generation has witnessed rapid progress, the inference results of existing models still exhibit unsatisfactory temporal consistency and unnatural dynamics. In this paper, we delve deep into the noise initialization of video diffusion models, and discover an implicit training-inference gap that attributes to the unsatisfactory inference quality.Our key findings are: 1) the spatial-temporal frequency distribution of the initial noise at inference is intrinsically different from that for training, and 2) the denoising process is significantly influenced by the low-fre"},"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":"2312.07537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T18:59:16Z","cross_cats_sorted":[],"title_canon_sha256":"da01fd455c3ef8014fc494e537fc0413987abf2c6d13b4d6a1a167616bf20c34","abstract_canon_sha256":"cfa2ccb6651dcd12e34cc7bcdc06c029de146bb339d7c7a44d957500d5dbf640"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:11.844335Z","signature_b64":"S44+pg87xAxHgD/IEMCd8XPCr/YiZSFe8M5HddzneSdtFJJiQo/XXDk1XvH90p7UWOOmvsHu/SNCgIR/RPSsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6d4761d83ae6ea4debce6261dba3c33d9a20555cdefd759699610eced734f47","last_reissued_at":"2026-07-05T08:48:11.843872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:11.843872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeInit: Bridging Initialization Gap in Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Si, Tianxing Wu, Yuming Jiang, Ziqi Huang, Ziwei Liu","submitted_at":"2023-12-12T18:59:16Z","abstract_excerpt":"Though diffusion-based video generation has witnessed rapid progress, the inference results of existing models still exhibit unsatisfactory temporal consistency and unnatural dynamics. In this paper, we delve deep into the noise initialization of video diffusion models, and discover an implicit training-inference gap that attributes to the unsatisfactory inference quality.Our key findings are: 1) the spatial-temporal frequency distribution of the initial noise at inference is intrinsically different from that for training, and 2) the denoising process is significantly influenced by the low-fre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07537","kind":"arxiv","version":2},"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/2312.07537/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":"2312.07537","created_at":"2026-07-05T08:48:11.843936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07537v2","created_at":"2026-07-05T08:48:11.843936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07537","created_at":"2026-07-05T08:48:11.843936+00:00"},{"alias_kind":"pith_short_12","alias_value":"23KHMHMDVZXK","created_at":"2026-07-05T08:48:11.843936+00:00"},{"alias_kind":"pith_short_16","alias_value":"23KHMHMDVZXKJXV4","created_at":"2026-07-05T08:48:11.843936+00:00"},{"alias_kind":"pith_short_8","alias_value":"23KHMHMD","created_at":"2026-07-05T08:48:11.843936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":209,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23KHMHMDVZXKJXV44YTB3OR4GP","json":"https://pith.science/pith/23KHMHMDVZXKJXV44YTB3OR4GP.json","graph_json":"https://pith.science/api/pith-number/23KHMHMDVZXKJXV44YTB3OR4GP/graph.json","events_json":"https://pith.science/api/pith-number/23KHMHMDVZXKJXV44YTB3OR4GP/events.json","paper":"https://pith.science/paper/23KHMHMD"},"agent_actions":{"view_html":"https://pith.science/pith/23KHMHMDVZXKJXV44YTB3OR4GP","download_json":"https://pith.science/pith/23KHMHMDVZXKJXV44YTB3OR4GP.json","view_paper":"https://pith.science/paper/23KHMHMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07537&json=true","fetch_graph":"https://pith.science/api/pith-number/23KHMHMDVZXKJXV44YTB3OR4GP/graph.json","fetch_events":"https://pith.science/api/pith-number/23KHMHMDVZXKJXV44YTB3OR4GP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23KHMHMDVZXKJXV44YTB3OR4GP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23KHMHMDVZXKJXV44YTB3OR4GP/action/storage_attestation","attest_author":"https://pith.science/pith/23KHMHMDVZXKJXV44YTB3OR4GP/action/author_attestation","sign_citation":"https://pith.science/pith/23KHMHMDVZXKJXV44YTB3OR4GP/action/citation_signature","submit_replication":"https://pith.science/pith/23KHMHMDVZXKJXV44YTB3OR4GP/action/replication_record"}},"created_at":"2026-07-05T08:48:11.843936+00:00","updated_at":"2026-07-05T08:48:11.843936+00:00"}