{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IHBVHX4HST6O2ST3XCBX4WG2M7","short_pith_number":"pith:IHBVHX4H","schema_version":"1.0","canonical_sha256":"41c353df8794fced4a7bb8837e58da67c214938d947f56b8c0f20db093ac2a16","source":{"kind":"arxiv","id":"2312.13834","version":1},"attestation_state":"computed","paper":{"title":"Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bichen Wu, Ching-Yao Chuang, Feng Liang, Kapil Krishnakumar, Licheng Yu, Peter Vajda, Tong Xiao, Xiaoyan Wang, Yichen Jia","submitted_at":"2023-12-20T01:49:47Z","abstract_excerpt":"In this paper, we introduce Fairy, a minimalist yet robust adaptation of image-editing diffusion models, enhancing them for video editing applications. Our approach centers on the concept of anchor-based cross-frame attention, a mechanism that implicitly propagates diffusion features across frames, ensuring superior temporal coherence and high-fidelity synthesis. Fairy not only addresses limitations of previous models, including memory and processing speed. It also improves temporal consistency through a unique data augmentation strategy. This strategy renders the model equivariant to affine t"},"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":"2312.13834","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-20T01:49:47Z","cross_cats_sorted":[],"title_canon_sha256":"794cc4312066fc782c7fe133f66c38e4376df82a566a2c298b1d324de7f0c96b","abstract_canon_sha256":"06d909a62b2d332bc281c261d86d0364356e656bff872f6a0c3b8f5e64ddf511"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:57.017291Z","signature_b64":"S0V8RDlJ76GgVvCqewjlEXq7Ro3kuFGEk+pZH90V3akFm7dcHbcL6SidXrDVyf0BM1arUD/+fODBV09ggniQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41c353df8794fced4a7bb8837e58da67c214938d947f56b8c0f20db093ac2a16","last_reissued_at":"2026-07-05T07:26:57.016854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:57.016854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bichen Wu, Ching-Yao Chuang, Feng Liang, Kapil Krishnakumar, Licheng Yu, Peter Vajda, Tong Xiao, Xiaoyan Wang, Yichen Jia","submitted_at":"2023-12-20T01:49:47Z","abstract_excerpt":"In this paper, we introduce Fairy, a minimalist yet robust adaptation of image-editing diffusion models, enhancing them for video editing applications. Our approach centers on the concept of anchor-based cross-frame attention, a mechanism that implicitly propagates diffusion features across frames, ensuring superior temporal coherence and high-fidelity synthesis. Fairy not only addresses limitations of previous models, including memory and processing speed. It also improves temporal consistency through a unique data augmentation strategy. This strategy renders the model equivariant to affine t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13834","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/2312.13834/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":"2312.13834","created_at":"2026-07-05T07:26:57.016914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13834v1","created_at":"2026-07-05T07:26:57.016914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13834","created_at":"2026-07-05T07:26:57.016914+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHBVHX4HST6O","created_at":"2026-07-05T07:26:57.016914+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHBVHX4HST6O2ST3","created_at":"2026-07-05T07:26:57.016914+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHBVHX4H","created_at":"2026-07-05T07:26:57.016914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":198,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHBVHX4HST6O2ST3XCBX4WG2M7","json":"https://pith.science/pith/IHBVHX4HST6O2ST3XCBX4WG2M7.json","graph_json":"https://pith.science/api/pith-number/IHBVHX4HST6O2ST3XCBX4WG2M7/graph.json","events_json":"https://pith.science/api/pith-number/IHBVHX4HST6O2ST3XCBX4WG2M7/events.json","paper":"https://pith.science/paper/IHBVHX4H"},"agent_actions":{"view_html":"https://pith.science/pith/IHBVHX4HST6O2ST3XCBX4WG2M7","download_json":"https://pith.science/pith/IHBVHX4HST6O2ST3XCBX4WG2M7.json","view_paper":"https://pith.science/paper/IHBVHX4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13834&json=true","fetch_graph":"https://pith.science/api/pith-number/IHBVHX4HST6O2ST3XCBX4WG2M7/graph.json","fetch_events":"https://pith.science/api/pith-number/IHBVHX4HST6O2ST3XCBX4WG2M7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHBVHX4HST6O2ST3XCBX4WG2M7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHBVHX4HST6O2ST3XCBX4WG2M7/action/storage_attestation","attest_author":"https://pith.science/pith/IHBVHX4HST6O2ST3XCBX4WG2M7/action/author_attestation","sign_citation":"https://pith.science/pith/IHBVHX4HST6O2ST3XCBX4WG2M7/action/citation_signature","submit_replication":"https://pith.science/pith/IHBVHX4HST6O2ST3XCBX4WG2M7/action/replication_record"}},"created_at":"2026-07-05T07:26:57.016914+00:00","updated_at":"2026-07-05T07:26:57.016914+00:00"}