{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KXMUXB6BCXZ2D6SGY2RTMU4E5V","short_pith_number":"pith:KXMUXB6B","schema_version":"1.0","canonical_sha256":"55d94b87c115f3a1fa46c6a3365384ed4e05b63cc2e8bbc8913990213b36d14b","source":{"kind":"arxiv","id":"2404.16306","version":1},"attestation_state":"computed","paper":{"title":"TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Bernhard Egger, Haomiao Ni, Sharon X. Huang, Suhas Lohit, Tim K. Marks, Toshiaki Koike-Akino, Ye Wang","submitted_at":"2024-04-25T03:21:11Z","abstract_excerpt":"Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g., a woman's photo) and a text description (e.g., \"a woman is drinking water.\"). Existing TI2V frameworks often require costly training on video-text datasets and specific model designs for text and image conditioning. In this paper, we propose TI2V-Zero, a zero-shot, tuning-free method that empowers a pretrained text-to-video (T2V) diffusion model to be conditioned on a provided image, enabling TI2V generation without any optimization, fine-tuning, or introducing external mod"},"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":"2404.16306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T03:21:11Z","cross_cats_sorted":[],"title_canon_sha256":"8b2f4af440eeb3267cba22b751c8dd4b8751b02c758d8cf0fbd204af219fc26a","abstract_canon_sha256":"30c3cd4e4f3144440442342c1e698f8385e0ad407ff8444e4374e60b5d19b565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:04.323031Z","signature_b64":"oawPz2N5jdNUmCurTqjU6xO8RjsN5wW9QScoiI66UknLQcspqYAHsy6/zm32CytgjRZaPfdp2OARTVc7VKIPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55d94b87c115f3a1fa46c6a3365384ed4e05b63cc2e8bbc8913990213b36d14b","last_reissued_at":"2026-07-05T08:12:04.322615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:04.322615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Bernhard Egger, Haomiao Ni, Sharon X. Huang, Suhas Lohit, Tim K. Marks, Toshiaki Koike-Akino, Ye Wang","submitted_at":"2024-04-25T03:21:11Z","abstract_excerpt":"Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g., a woman's photo) and a text description (e.g., \"a woman is drinking water.\"). Existing TI2V frameworks often require costly training on video-text datasets and specific model designs for text and image conditioning. In this paper, we propose TI2V-Zero, a zero-shot, tuning-free method that empowers a pretrained text-to-video (T2V) diffusion model to be conditioned on a provided image, enabling TI2V generation without any optimization, fine-tuning, or introducing external mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16306","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/2404.16306/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":"2404.16306","created_at":"2026-07-05T08:12:04.322680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16306v1","created_at":"2026-07-05T08:12:04.322680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16306","created_at":"2026-07-05T08:12:04.322680+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXMUXB6BCXZ2","created_at":"2026-07-05T08:12:04.322680+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXMUXB6BCXZ2D6SG","created_at":"2026-07-05T08:12:04.322680+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXMUXB6B","created_at":"2026-07-05T08:12:04.322680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXMUXB6BCXZ2D6SGY2RTMU4E5V","json":"https://pith.science/pith/KXMUXB6BCXZ2D6SGY2RTMU4E5V.json","graph_json":"https://pith.science/api/pith-number/KXMUXB6BCXZ2D6SGY2RTMU4E5V/graph.json","events_json":"https://pith.science/api/pith-number/KXMUXB6BCXZ2D6SGY2RTMU4E5V/events.json","paper":"https://pith.science/paper/KXMUXB6B"},"agent_actions":{"view_html":"https://pith.science/pith/KXMUXB6BCXZ2D6SGY2RTMU4E5V","download_json":"https://pith.science/pith/KXMUXB6BCXZ2D6SGY2RTMU4E5V.json","view_paper":"https://pith.science/paper/KXMUXB6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16306&json=true","fetch_graph":"https://pith.science/api/pith-number/KXMUXB6BCXZ2D6SGY2RTMU4E5V/graph.json","fetch_events":"https://pith.science/api/pith-number/KXMUXB6BCXZ2D6SGY2RTMU4E5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXMUXB6BCXZ2D6SGY2RTMU4E5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXMUXB6BCXZ2D6SGY2RTMU4E5V/action/storage_attestation","attest_author":"https://pith.science/pith/KXMUXB6BCXZ2D6SGY2RTMU4E5V/action/author_attestation","sign_citation":"https://pith.science/pith/KXMUXB6BCXZ2D6SGY2RTMU4E5V/action/citation_signature","submit_replication":"https://pith.science/pith/KXMUXB6BCXZ2D6SGY2RTMU4E5V/action/replication_record"}},"created_at":"2026-07-05T08:12:04.322680+00:00","updated_at":"2026-07-05T08:12:04.322680+00:00"}