{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UV6SWSM6LIJTEOQUXGODHZ4CED","short_pith_number":"pith:UV6SWSM6","schema_version":"1.0","canonical_sha256":"a57d2b499e5a13323a14b99c33e78220f49383992c8e0ddbec79a501c85ede2b","source":{"kind":"arxiv","id":"2312.00330","version":2},"attestation_state":"computed","paper":{"title":"StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gongye Liu, Haoxin Chen, Jinbo Xing, Menghan Xia, Xintao Wang, Yibo Wang, Ying Shan, Yong Zhang, Yujiu Yang","submitted_at":"2023-12-01T03:53:21Z","abstract_excerpt":"Text-to-video (T2V) models have shown remarkable capabilities in generating diverse videos. However, they struggle to produce user-desired stylized videos due to (i) text's inherent clumsiness in expressing specific styles and (ii) the generally degraded style fidelity. To address these challenges, we introduce StyleCrafter, a generic method that enhances pre-trained T2V models with a style control adapter, enabling video generation in any style by providing a reference image. Considering the scarcity of stylized video datasets, we propose to first train a style control adapter using style-ric"},"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":"2312.00330","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T03:53:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d62de3025a83a1891fc3c2fb1bfc6c0d65b3bcc37164481ee472c05ab393922","abstract_canon_sha256":"045e77ca8b5b75eb7028fb54853b4f4e8b7938a1a4c32de5e9ddda8c2132be38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:01.521450Z","signature_b64":"Bxat2Eckg5ZenkNveNCKCGwm+gmDDI25UvgJjKCt/UWNY71FmzJSV/FJN0zt69U+NFSu24LWe6jgE8IznfivDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a57d2b499e5a13323a14b99c33e78220f49383992c8e0ddbec79a501c85ede2b","last_reissued_at":"2026-07-05T09:06:01.520960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:01.520960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gongye Liu, Haoxin Chen, Jinbo Xing, Menghan Xia, Xintao Wang, Yibo Wang, Ying Shan, Yong Zhang, Yujiu Yang","submitted_at":"2023-12-01T03:53:21Z","abstract_excerpt":"Text-to-video (T2V) models have shown remarkable capabilities in generating diverse videos. However, they struggle to produce user-desired stylized videos due to (i) text's inherent clumsiness in expressing specific styles and (ii) the generally degraded style fidelity. To address these challenges, we introduce StyleCrafter, a generic method that enhances pre-trained T2V models with a style control adapter, enabling video generation in any style by providing a reference image. Considering the scarcity of stylized video datasets, we propose to first train a style control adapter using style-ric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00330","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/2312.00330/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":"2312.00330","created_at":"2026-07-05T09:06:01.521027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00330v2","created_at":"2026-07-05T09:06:01.521027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00330","created_at":"2026-07-05T09:06:01.521027+00:00"},{"alias_kind":"pith_short_12","alias_value":"UV6SWSM6LIJT","created_at":"2026-07-05T09:06:01.521027+00:00"},{"alias_kind":"pith_short_16","alias_value":"UV6SWSM6LIJTEOQU","created_at":"2026-07-05T09:06:01.521027+00:00"},{"alias_kind":"pith_short_8","alias_value":"UV6SWSM6","created_at":"2026-07-05T09:06:01.521027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06162","citing_title":"High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08364","citing_title":"MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07257","citing_title":"Adaptive Subspace Projection for Generative Personalization","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UV6SWSM6LIJTEOQUXGODHZ4CED","json":"https://pith.science/pith/UV6SWSM6LIJTEOQUXGODHZ4CED.json","graph_json":"https://pith.science/api/pith-number/UV6SWSM6LIJTEOQUXGODHZ4CED/graph.json","events_json":"https://pith.science/api/pith-number/UV6SWSM6LIJTEOQUXGODHZ4CED/events.json","paper":"https://pith.science/paper/UV6SWSM6"},"agent_actions":{"view_html":"https://pith.science/pith/UV6SWSM6LIJTEOQUXGODHZ4CED","download_json":"https://pith.science/pith/UV6SWSM6LIJTEOQUXGODHZ4CED.json","view_paper":"https://pith.science/paper/UV6SWSM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00330&json=true","fetch_graph":"https://pith.science/api/pith-number/UV6SWSM6LIJTEOQUXGODHZ4CED/graph.json","fetch_events":"https://pith.science/api/pith-number/UV6SWSM6LIJTEOQUXGODHZ4CED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UV6SWSM6LIJTEOQUXGODHZ4CED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UV6SWSM6LIJTEOQUXGODHZ4CED/action/storage_attestation","attest_author":"https://pith.science/pith/UV6SWSM6LIJTEOQUXGODHZ4CED/action/author_attestation","sign_citation":"https://pith.science/pith/UV6SWSM6LIJTEOQUXGODHZ4CED/action/citation_signature","submit_replication":"https://pith.science/pith/UV6SWSM6LIJTEOQUXGODHZ4CED/action/replication_record"}},"created_at":"2026-07-05T09:06:01.521027+00:00","updated_at":"2026-07-05T09:06:01.521027+00:00"}