{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:34HB6Z2APCYDQR36GQQ55XAUDA","short_pith_number":"pith:34HB6Z2A","schema_version":"1.0","canonical_sha256":"df0e1f674078b038477e3421dedc1418270766ba841e25e12dbe381e33eb3535","source":{"kind":"arxiv","id":"2309.01770","version":2},"attestation_state":"computed","paper":{"title":"StyleAdapter: A Unified Stylized Image Generation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liangbin Xie, Ping Luo, Wenping Wang, Xintao Wang, Ying Shan, Zhongang Qi, Zhouxia Wang","submitted_at":"2023-09-04T19:16:46Z","abstract_excerpt":"This work focuses on generating high-quality images with specific style of reference images and content of provided textual descriptions. Current leading algorithms, i.e., DreamBooth and LoRA, require fine-tuning for each style, leading to time-consuming and computationally expensive processes. In this work, we propose StyleAdapter, a unified stylized image generation model capable of producing a variety of stylized images that match both the content of a given prompt and the style of reference images, without the need for per-style fine-tuning. It introduces a two-path cross-attention (TPCA) "},"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":"2309.01770","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T19:16:46Z","cross_cats_sorted":[],"title_canon_sha256":"5aeb60c9e25215c38ead1eeea04070072d5dc27939ee2b22cb87f3c24c3f225b","abstract_canon_sha256":"2f269bcdb928dc986f8e4c24d1769d97d33cc8ce0da2ae21f513a59e195c06a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:27.561576Z","signature_b64":"ZJzlJToX5sG7RlZhuWRK5cYfq9dX+J98TdvsMFgcRxLsRdzo1EyuKKPgNRqHZ6o+kZChm0Hf/nHzmc7rLQyGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df0e1f674078b038477e3421dedc1418270766ba841e25e12dbe381e33eb3535","last_reissued_at":"2026-07-05T09:28:27.561112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:27.561112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StyleAdapter: A Unified Stylized Image Generation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liangbin Xie, Ping Luo, Wenping Wang, Xintao Wang, Ying Shan, Zhongang Qi, Zhouxia Wang","submitted_at":"2023-09-04T19:16:46Z","abstract_excerpt":"This work focuses on generating high-quality images with specific style of reference images and content of provided textual descriptions. Current leading algorithms, i.e., DreamBooth and LoRA, require fine-tuning for each style, leading to time-consuming and computationally expensive processes. In this work, we propose StyleAdapter, a unified stylized image generation model capable of producing a variety of stylized images that match both the content of a given prompt and the style of reference images, without the need for per-style fine-tuning. It introduces a two-path cross-attention (TPCA) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01770","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/2309.01770/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":"2309.01770","created_at":"2026-07-05T09:28:27.561171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01770v2","created_at":"2026-07-05T09:28:27.561171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01770","created_at":"2026-07-05T09:28:27.561171+00:00"},{"alias_kind":"pith_short_12","alias_value":"34HB6Z2APCYD","created_at":"2026-07-05T09:28:27.561171+00:00"},{"alias_kind":"pith_short_16","alias_value":"34HB6Z2APCYDQR36","created_at":"2026-07-05T09:28:27.561171+00:00"},{"alias_kind":"pith_short_8","alias_value":"34HB6Z2A","created_at":"2026-07-05T09:28:27.561171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14746","citing_title":"Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2412.12242","citing_title":"OmniPrism: Learning Disentangled Visual Concept for Image Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19034","citing_title":"Color Conditional Generation with Sliced Wasserstein Guidance","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12598","citing_title":"Setting the Stage: Text-Driven Scene-Consistent Image Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17312","citing_title":"VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08364","citing_title":"MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/34HB6Z2APCYDQR36GQQ55XAUDA","json":"https://pith.science/pith/34HB6Z2APCYDQR36GQQ55XAUDA.json","graph_json":"https://pith.science/api/pith-number/34HB6Z2APCYDQR36GQQ55XAUDA/graph.json","events_json":"https://pith.science/api/pith-number/34HB6Z2APCYDQR36GQQ55XAUDA/events.json","paper":"https://pith.science/paper/34HB6Z2A"},"agent_actions":{"view_html":"https://pith.science/pith/34HB6Z2APCYDQR36GQQ55XAUDA","download_json":"https://pith.science/pith/34HB6Z2APCYDQR36GQQ55XAUDA.json","view_paper":"https://pith.science/paper/34HB6Z2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01770&json=true","fetch_graph":"https://pith.science/api/pith-number/34HB6Z2APCYDQR36GQQ55XAUDA/graph.json","fetch_events":"https://pith.science/api/pith-number/34HB6Z2APCYDQR36GQQ55XAUDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34HB6Z2APCYDQR36GQQ55XAUDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34HB6Z2APCYDQR36GQQ55XAUDA/action/storage_attestation","attest_author":"https://pith.science/pith/34HB6Z2APCYDQR36GQQ55XAUDA/action/author_attestation","sign_citation":"https://pith.science/pith/34HB6Z2APCYDQR36GQQ55XAUDA/action/citation_signature","submit_replication":"https://pith.science/pith/34HB6Z2APCYDQR36GQQ55XAUDA/action/replication_record"}},"created_at":"2026-07-05T09:28:27.561171+00:00","updated_at":"2026-07-05T09:28:27.561171+00:00"}