{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F5OQYRSNQFLNWM4OHEC6LPTHAE","short_pith_number":"pith:F5OQYRSN","schema_version":"1.0","canonical_sha256":"2f5d0c464d8156db338e3905e5be67012dc41effa8fea867da5bada3b8ed6243","source":{"kind":"arxiv","id":"2311.04145","version":1},"attestation_state":"computed","paper":{"title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deli Zhao, Hangjie Yuan, Jiayu Wang, Jingren Zhou, Kang Zhao, Shiwei Zhang, Xiang Wang, Yingya Zhang, Zhiwu Qin","submitted_at":"2023-11-07T17:16:06Z","abstract_excerpt":"Video synthesis has recently made remarkable strides benefiting from the rapid development of diffusion models. However, it still encounters challenges in terms of semantic accuracy, clarity and spatio-temporal continuity. They primarily arise from the scarcity of well-aligned text-video data and the complex inherent structure of videos, making it difficult for the model to simultaneously ensure semantic and qualitative excellence. In this report, we propose a cascaded I2VGen-XL approach that enhances model performance by decoupling these two factors and ensures the alignment of the input data"},"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":"2311.04145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T17:16:06Z","cross_cats_sorted":[],"title_canon_sha256":"463aebdc2591e5cedd897bdf457d6ff329f77156d5c00c398df35bdbecbd84e5","abstract_canon_sha256":"f2d0adc1d96d3c17ed39de6f450a0dad9f2503244156a80a09ce1e0fdccf0aa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:49.010191Z","signature_b64":"tHTocHGNjuVSXUkyg8GaUm/zhHdBE4qlRLCjumqtLm17J/vMEqVTovpIdBK1pG28M1I/zLa9dPEWB4cKZyTZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f5d0c464d8156db338e3905e5be67012dc41effa8fea867da5bada3b8ed6243","last_reissued_at":"2026-05-17T23:46:49.009689Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:49.009689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deli Zhao, Hangjie Yuan, Jiayu Wang, Jingren Zhou, Kang Zhao, Shiwei Zhang, Xiang Wang, Yingya Zhang, Zhiwu Qin","submitted_at":"2023-11-07T17:16:06Z","abstract_excerpt":"Video synthesis has recently made remarkable strides benefiting from the rapid development of diffusion models. However, it still encounters challenges in terms of semantic accuracy, clarity and spatio-temporal continuity. They primarily arise from the scarcity of well-aligned text-video data and the complex inherent structure of videos, making it difficult for the model to simultaneously ensure semantic and qualitative excellence. In this report, we propose a cascaded I2VGen-XL approach that enhances model performance by decoupling these two factors and ensures the alignment of the input data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04145","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":""},"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":"2311.04145","created_at":"2026-05-17T23:46:49.009769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04145v1","created_at":"2026-05-17T23:46:49.009769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04145","created_at":"2026-05-17T23:46:49.009769+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5OQYRSNQFLN","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5OQYRSNQFLNWM4O","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5OQYRSN","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":17,"sample":[{"citing_arxiv_id":"2602.07775","citing_title":"Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion","ref_index":110,"is_internal_anchor":true},{"citing_arxiv_id":"2503.07598","citing_title":"VACE: All-in-One Video Creation and Editing","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2508.00795","citing_title":"Video Generators are Robot Policies","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14487","citing_title":"Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2404.02101","citing_title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","ref_index":167,"is_internal_anchor":true},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":144,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06356","citing_title":"SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23574","citing_title":"PhysLayer: Language-Guided Layered Animation with Depth-Aware Physics","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06356","citing_title":"SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04569","citing_title":"Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01517","citing_title":"VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation","ref_index":223,"is_internal_anchor":true},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10837","citing_title":"Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12219","citing_title":"Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2501.00103","citing_title":"LTX-Video: Realtime Video Latent Diffusion","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2311.15127","citing_title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","ref_index":113,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17749","citing_title":"Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE","json":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE.json","graph_json":"https://pith.science/api/pith-number/F5OQYRSNQFLNWM4OHEC6LPTHAE/graph.json","events_json":"https://pith.science/api/pith-number/F5OQYRSNQFLNWM4OHEC6LPTHAE/events.json","paper":"https://pith.science/paper/F5OQYRSN"},"agent_actions":{"view_html":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE","download_json":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE.json","view_paper":"https://pith.science/paper/F5OQYRSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04145&json=true","fetch_graph":"https://pith.science/api/pith-number/F5OQYRSNQFLNWM4OHEC6LPTHAE/graph.json","fetch_events":"https://pith.science/api/pith-number/F5OQYRSNQFLNWM4OHEC6LPTHAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/action/storage_attestation","attest_author":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/action/author_attestation","sign_citation":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/action/citation_signature","submit_replication":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/action/replication_record"}},"created_at":"2026-05-17T23:46:49.009769+00:00","updated_at":"2026-05-17T23:46:49.009769+00:00"}