{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QX2M2SGYAG7BL6BEA3UVA7XV7K","short_pith_number":"pith:QX2M2SGY","schema_version":"1.0","canonical_sha256":"85f4cd48d801be15f82406e9507ef5fa908dd5e33e9a441d50a57383845995c4","source":{"kind":"arxiv","id":"2212.11565","version":2},"attestation_state":"computed","paper":{"title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jay Zhangjie Wu, Mike Zheng Shou, Weixian Lei, Wynne Hsu, Xiaohu Qie, Xintao Wang, Ying Shan, Yixiao Ge, Yuchao Gu, Yufei Shi","submitted_at":"2022-12-22T09:43:36Z","abstract_excerpt":"To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator. Despite their promising results, such paradigm is computationally expensive. In this work, we propose a new T2V generation setting$\\unicode{x2014}$One-Shot Video Tuning, where only one text-video pair is presented. Our model is built on state-of-the-art T2I diffusion models pre-trained on massive image data. We make two key observations: 1) T2I models can generate still images that represent verb terms; 2) extending T2I models to generate multiple"},"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":"2212.11565","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-22T09:43:36Z","cross_cats_sorted":[],"title_canon_sha256":"5093d93bc8b012e3ef972e7ab32be719e007726eccbfb29cbefb22db5f659d88","abstract_canon_sha256":"7ac96680dd6190cfb8efc93d401f8989fb94366ad4293533c3a232718405a524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:09.364764Z","signature_b64":"zUf0jgtv3lVUfL5YFOyC/2d2gz2prTbOuorilUMleI02S78RlnPNlx8n5zy9AqGSueXBUfX0TuhUw0HCkFRWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85f4cd48d801be15f82406e9507ef5fa908dd5e33e9a441d50a57383845995c4","last_reissued_at":"2026-07-05T05:52:09.364220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:09.364220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jay Zhangjie Wu, Mike Zheng Shou, Weixian Lei, Wynne Hsu, Xiaohu Qie, Xintao Wang, Ying Shan, Yixiao Ge, Yuchao Gu, Yufei Shi","submitted_at":"2022-12-22T09:43:36Z","abstract_excerpt":"To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator. Despite their promising results, such paradigm is computationally expensive. In this work, we propose a new T2V generation setting$\\unicode{x2014}$One-Shot Video Tuning, where only one text-video pair is presented. Our model is built on state-of-the-art T2I diffusion models pre-trained on massive image data. We make two key observations: 1) T2I models can generate still images that represent verb terms; 2) extending T2I models to generate multiple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11565","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/2212.11565/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":"2212.11565","created_at":"2026-07-05T05:52:09.364291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.11565v2","created_at":"2026-07-05T05:52:09.364291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11565","created_at":"2026-07-05T05:52:09.364291+00:00"},{"alias_kind":"pith_short_12","alias_value":"QX2M2SGYAG7B","created_at":"2026-07-05T05:52:09.364291+00:00"},{"alias_kind":"pith_short_16","alias_value":"QX2M2SGYAG7BL6BE","created_at":"2026-07-05T05:52:09.364291+00:00"},{"alias_kind":"pith_short_8","alias_value":"QX2M2SGY","created_at":"2026-07-05T05:52:09.364291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05665","citing_title":"V2V-Bench: A Comprehensive Benchmark for Video-to-Video Generation Evaluation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2411.19182","citing_title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":249,"is_internal_anchor":false},{"citing_arxiv_id":"2307.10373","citing_title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2310.00426","citing_title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05898","citing_title":"Physics-Aware Video Instance Removal Benchmark","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QX2M2SGYAG7BL6BEA3UVA7XV7K","json":"https://pith.science/pith/QX2M2SGYAG7BL6BEA3UVA7XV7K.json","graph_json":"https://pith.science/api/pith-number/QX2M2SGYAG7BL6BEA3UVA7XV7K/graph.json","events_json":"https://pith.science/api/pith-number/QX2M2SGYAG7BL6BEA3UVA7XV7K/events.json","paper":"https://pith.science/paper/QX2M2SGY"},"agent_actions":{"view_html":"https://pith.science/pith/QX2M2SGYAG7BL6BEA3UVA7XV7K","download_json":"https://pith.science/pith/QX2M2SGYAG7BL6BEA3UVA7XV7K.json","view_paper":"https://pith.science/paper/QX2M2SGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.11565&json=true","fetch_graph":"https://pith.science/api/pith-number/QX2M2SGYAG7BL6BEA3UVA7XV7K/graph.json","fetch_events":"https://pith.science/api/pith-number/QX2M2SGYAG7BL6BEA3UVA7XV7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QX2M2SGYAG7BL6BEA3UVA7XV7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QX2M2SGYAG7BL6BEA3UVA7XV7K/action/storage_attestation","attest_author":"https://pith.science/pith/QX2M2SGYAG7BL6BEA3UVA7XV7K/action/author_attestation","sign_citation":"https://pith.science/pith/QX2M2SGYAG7BL6BEA3UVA7XV7K/action/citation_signature","submit_replication":"https://pith.science/pith/QX2M2SGYAG7BL6BEA3UVA7XV7K/action/replication_record"}},"created_at":"2026-07-05T05:52:09.364291+00:00","updated_at":"2026-07-05T05:52:09.364291+00:00"}