{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5AYBQJ7TWEYMM2TD3IUGWMXEBL","short_pith_number":"pith:5AYBQJ7T","schema_version":"1.0","canonical_sha256":"e8301827f3b130c66a63da286b32e40ae697d28e7888d6d7cc3dc6c7a1e17f3f","source":{"kind":"arxiv","id":"2310.07697","version":2},"attestation_state":"computed","paper":{"title":"ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Peng, Chaochao Lu, Xinyuan Chen, Yaohui Wang, Yu Qiao","submitted_at":"2023-10-11T17:46:28Z","abstract_excerpt":"Recent works have successfully extended large-scale text-to-image models to the video domain, producing promising results but at a high computational cost and requiring a large amount of video data. In this work, we introduce ConditionVideo, a training-free approach to text-to-video generation based on the provided condition, video, and input text, by leveraging the power of off-the-shelf text-to-image generation methods (e.g., Stable Diffusion). ConditionVideo generates realistic dynamic videos from random noise or given scene videos. Our method explicitly disentangles the motion representati"},"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":"2310.07697","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:46:28Z","cross_cats_sorted":[],"title_canon_sha256":"b7542514f5c48edae360453c351c3058c4e9f521cc0582b6bc3ed97bb606b221","abstract_canon_sha256":"004dc3d3e883553c6e952ed7434100d643c43ce7967481ec9bec93b5c80162a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:21.498270Z","signature_b64":"wmKqZRIEZn7UJh/T2KhUDgcovzEDbRfigDkz9EI0liAarsIXjpMtUNmCj2EnKAbNgegWV1T6pkqLijNpuWCcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8301827f3b130c66a63da286b32e40ae697d28e7888d6d7cc3dc6c7a1e17f3f","last_reissued_at":"2026-07-05T08:22:21.497801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:21.497801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Peng, Chaochao Lu, Xinyuan Chen, Yaohui Wang, Yu Qiao","submitted_at":"2023-10-11T17:46:28Z","abstract_excerpt":"Recent works have successfully extended large-scale text-to-image models to the video domain, producing promising results but at a high computational cost and requiring a large amount of video data. In this work, we introduce ConditionVideo, a training-free approach to text-to-video generation based on the provided condition, video, and input text, by leveraging the power of off-the-shelf text-to-image generation methods (e.g., Stable Diffusion). ConditionVideo generates realistic dynamic videos from random noise or given scene videos. Our method explicitly disentangles the motion representati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07697","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/2310.07697/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":"2310.07697","created_at":"2026-07-05T08:22:21.497857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07697v2","created_at":"2026-07-05T08:22:21.497857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07697","created_at":"2026-07-05T08:22:21.497857+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AYBQJ7TWEYM","created_at":"2026-07-05T08:22:21.497857+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AYBQJ7TWEYMM2TD","created_at":"2026-07-05T08:22:21.497857+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AYBQJ7T","created_at":"2026-07-05T08:22:21.497857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01343","citing_title":"MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AYBQJ7TWEYMM2TD3IUGWMXEBL","json":"https://pith.science/pith/5AYBQJ7TWEYMM2TD3IUGWMXEBL.json","graph_json":"https://pith.science/api/pith-number/5AYBQJ7TWEYMM2TD3IUGWMXEBL/graph.json","events_json":"https://pith.science/api/pith-number/5AYBQJ7TWEYMM2TD3IUGWMXEBL/events.json","paper":"https://pith.science/paper/5AYBQJ7T"},"agent_actions":{"view_html":"https://pith.science/pith/5AYBQJ7TWEYMM2TD3IUGWMXEBL","download_json":"https://pith.science/pith/5AYBQJ7TWEYMM2TD3IUGWMXEBL.json","view_paper":"https://pith.science/paper/5AYBQJ7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07697&json=true","fetch_graph":"https://pith.science/api/pith-number/5AYBQJ7TWEYMM2TD3IUGWMXEBL/graph.json","fetch_events":"https://pith.science/api/pith-number/5AYBQJ7TWEYMM2TD3IUGWMXEBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AYBQJ7TWEYMM2TD3IUGWMXEBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AYBQJ7TWEYMM2TD3IUGWMXEBL/action/storage_attestation","attest_author":"https://pith.science/pith/5AYBQJ7TWEYMM2TD3IUGWMXEBL/action/author_attestation","sign_citation":"https://pith.science/pith/5AYBQJ7TWEYMM2TD3IUGWMXEBL/action/citation_signature","submit_replication":"https://pith.science/pith/5AYBQJ7TWEYMM2TD3IUGWMXEBL/action/replication_record"}},"created_at":"2026-07-05T08:22:21.497857+00:00","updated_at":"2026-07-05T08:22:21.497857+00:00"}