{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4ZVQJD6UAPPG6ELL3QINWN4WWF","short_pith_number":"pith:4ZVQJD6U","schema_version":"1.0","canonical_sha256":"e66b048fd403de6f116bdc10db3796b1491fca2c929748c729c6372b9fe48c62","source":{"kind":"arxiv","id":"2307.10373","version":3},"attestation_state":"computed","paper":{"title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michal Geyer, Omer Bar-Tal, Shai Bagon, Tali Dekel","submitted_at":"2023-07-19T18:00:03Z","abstract_excerpt":"The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key obse"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.10373","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T18:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"dbea7345e122a1e97e220cee9e14684f92d07d9632b7f26ed75e64ce59eb04e7","abstract_canon_sha256":"b96ec8c6351673bf7ed8019ebd9f1eb0f2ee97edac7e2bd78e5884173c3ed0cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.200853Z","signature_b64":"PPVdOKv5ctFlpRIfBlz7IG3odD5gqnBF9/1N0TrB+ae7C7cnUPKcrQ1Wqwdg0V3+YNJ06jQu/UF0m5nWaq9JDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e66b048fd403de6f116bdc10db3796b1491fca2c929748c729c6372b9fe48c62","last_reissued_at":"2026-05-17T23:38:13.200350Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.200350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michal Geyer, Omer Bar-Tal, Shai Bagon, Tali Dekel","submitted_at":"2023-07-19T18:00:03Z","abstract_excerpt":"The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key obse"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space... by explicitly propagating diffusion features based on inter-frame correspondences","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That propagating diffusion features according to inter-frame correspondences will produce spatially and temporally consistent edits without introducing new artifacts or breaking the text conditioning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4ccb249b00a6a7e3e13d95681f3b8f30d3b6fafe43474d8898a78c5199fb930d"},"source":{"id":"2307.10373","kind":"arxiv","version":3},"verdict":{"id":"7f5d009a-ce61-46d1-9840-926ab35d5e64","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T20:12:21.562760Z","strongest_claim":"consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space... by explicitly propagating diffusion features based on inter-frame correspondences","one_line_summary":"TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That propagating diffusion features according to inter-frame correspondences will produce spatially and temporally consistent edits without introducing new artifacts or breaking the text conditioning.","pith_extraction_headline":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits."},"references":{"count":27,"sample":[{"doi":"","year":null,"title":"Multidiffusion: Fusing diffusion paths for controlled image generation","work_id":"1a06e9b7-e97f-4665-ba6e-55301822d3b6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Pix2video: Video editing using image diffusion","work_id":"9a64fd9d-fb53-46a1-8edb-808f1a5cd594","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models","work_id":"92bbf1bb-4319-45c4-845c-523bfc2cb97b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Diffusion models in vision: A survey.arXiv e-prints, abs/2209.04747","work_id":"46a3884e-d8d0-426d-873e-9096d96da38d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Structure and content-guided video synthesis with diffusion models","work_id":"9ec84ad8-517d-4d27-ba1a-447562d63988","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":27,"snapshot_sha256":"1458884d8ae3174bd27a627983cb5513060573d2271a44c8fca28fb9a36dc743","internal_anchors":7},"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":"2307.10373","created_at":"2026-05-17T23:38:13.200437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10373v3","created_at":"2026-05-17T23:38:13.200437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10373","created_at":"2026-05-17T23:38:13.200437+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZVQJD6UAPPG","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZVQJD6UAPPG6ELL","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZVQJD6U","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":20,"sample":[{"citing_arxiv_id":"2605.17019","citing_title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2509.04123","citing_title":"TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2509.18831","citing_title":"Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2510.01186","citing_title":"ASTRA: Let Arbitrary Subjects Transform in Video Editing","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17844","citing_title":"Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2512.07951","citing_title":"Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2312.14125","citing_title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02870","citing_title":"Token Warping Helps MLLMs Look from Nearby Viewpoints","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12271","citing_title":"Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21921","citing_title":"Context Unrolling in Omni Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10784","citing_title":"TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08646","citing_title":"InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05898","citing_title":"Physics-Aware Video Instance Removal Benchmark","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13509","citing_title":"DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13906","citing_title":"Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14556","citing_title":"Controllable Video Object Insertion via Multiview Priors","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":277,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF","json":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF.json","graph_json":"https://pith.science/api/pith-number/4ZVQJD6UAPPG6ELL3QINWN4WWF/graph.json","events_json":"https://pith.science/api/pith-number/4ZVQJD6UAPPG6ELL3QINWN4WWF/events.json","paper":"https://pith.science/paper/4ZVQJD6U"},"agent_actions":{"view_html":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF","download_json":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF.json","view_paper":"https://pith.science/paper/4ZVQJD6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10373&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZVQJD6UAPPG6ELL3QINWN4WWF/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZVQJD6UAPPG6ELL3QINWN4WWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/action/storage_attestation","attest_author":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/action/author_attestation","sign_citation":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/action/citation_signature","submit_replication":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/action/replication_record"}},"created_at":"2026-05-17T23:38:13.200437+00:00","updated_at":"2026-05-17T23:38:13.200437+00:00"}