{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YN5PNLDE4KATQH5P3KA4LIPOF2","short_pith_number":"pith:YN5PNLDE","schema_version":"1.0","canonical_sha256":"c37af6ac64e281381fafda81c5a1ee2eb6195baa89000eee2543b8a542b91c3c","source":{"kind":"arxiv","id":"2303.09535","version":3},"attestation_state":"computed","paper":{"title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Lei, Chenyang Qi, Qifeng Chen, Xiaodong Cun, Xintao Wang, Ying Shan, Yong Zhang","submitted_at":"2023-03-16T17:51:13Z","abstract_excerpt":"The diffusion-based generative models have achieved remarkable success in text-based image generation. However, since it contains enormous randomness in generation progress, it is still challenging to apply such models for real-world visual content editing, especially in videos. In this paper, we propose FateZero, a zero-shot text-based editing method on real-world videos without per-prompt training or use-specific mask. To edit videos consistently, we propose several techniques based on the pre-trained models. Firstly, in contrast to the straightforward DDIM inversion technique, our approach "},"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":"2303.09535","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T17:51:13Z","cross_cats_sorted":[],"title_canon_sha256":"f817cf581d01ee5d75a2e2cfc476e3d0fe827e206ae99df74d77f6ff45effb90","abstract_canon_sha256":"bba2fd37b4a3c4bfb3b50a531b11c2afb952aefba8fd44309a7898bb180e5e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:30.505052Z","signature_b64":"DkEXw38D1f9egvYbhz03Kl6KwcbqEwTs3xkhzNFSbKkhmKbMW+19ykl6hLi5IA7XoHLmoXMkdG66Z05UXiBACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c37af6ac64e281381fafda81c5a1ee2eb6195baa89000eee2543b8a542b91c3c","last_reissued_at":"2026-07-05T06:59:30.504609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:30.504609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Lei, Chenyang Qi, Qifeng Chen, Xiaodong Cun, Xintao Wang, Ying Shan, Yong Zhang","submitted_at":"2023-03-16T17:51:13Z","abstract_excerpt":"The diffusion-based generative models have achieved remarkable success in text-based image generation. However, since it contains enormous randomness in generation progress, it is still challenging to apply such models for real-world visual content editing, especially in videos. In this paper, we propose FateZero, a zero-shot text-based editing method on real-world videos without per-prompt training or use-specific mask. To edit videos consistently, we propose several techniques based on the pre-trained models. Firstly, in contrast to the straightforward DDIM inversion technique, our approach "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09535","kind":"arxiv","version":3},"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/2303.09535/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":"2303.09535","created_at":"2026-07-05T06:59:30.504667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09535v3","created_at":"2026-07-05T06:59:30.504667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09535","created_at":"2026-07-05T06:59:30.504667+00:00"},{"alias_kind":"pith_short_12","alias_value":"YN5PNLDE4KAT","created_at":"2026-07-05T06:59:30.504667+00:00"},{"alias_kind":"pith_short_16","alias_value":"YN5PNLDE4KATQH5P","created_at":"2026-07-05T06:59:30.504667+00:00"},{"alias_kind":"pith_short_8","alias_value":"YN5PNLDE","created_at":"2026-07-05T06:59:30.504667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23245","citing_title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05342","citing_title":"Delta Rectified Flow Sampling for Text-to-Image Editing","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2307.10373","citing_title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YN5PNLDE4KATQH5P3KA4LIPOF2","json":"https://pith.science/pith/YN5PNLDE4KATQH5P3KA4LIPOF2.json","graph_json":"https://pith.science/api/pith-number/YN5PNLDE4KATQH5P3KA4LIPOF2/graph.json","events_json":"https://pith.science/api/pith-number/YN5PNLDE4KATQH5P3KA4LIPOF2/events.json","paper":"https://pith.science/paper/YN5PNLDE"},"agent_actions":{"view_html":"https://pith.science/pith/YN5PNLDE4KATQH5P3KA4LIPOF2","download_json":"https://pith.science/pith/YN5PNLDE4KATQH5P3KA4LIPOF2.json","view_paper":"https://pith.science/paper/YN5PNLDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09535&json=true","fetch_graph":"https://pith.science/api/pith-number/YN5PNLDE4KATQH5P3KA4LIPOF2/graph.json","fetch_events":"https://pith.science/api/pith-number/YN5PNLDE4KATQH5P3KA4LIPOF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YN5PNLDE4KATQH5P3KA4LIPOF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YN5PNLDE4KATQH5P3KA4LIPOF2/action/storage_attestation","attest_author":"https://pith.science/pith/YN5PNLDE4KATQH5P3KA4LIPOF2/action/author_attestation","sign_citation":"https://pith.science/pith/YN5PNLDE4KATQH5P3KA4LIPOF2/action/citation_signature","submit_replication":"https://pith.science/pith/YN5PNLDE4KATQH5P3KA4LIPOF2/action/replication_record"}},"created_at":"2026-07-05T06:59:30.504667+00:00","updated_at":"2026-07-05T06:59:30.504667+00:00"}