{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RQKUTSSD4TTQ3T33GD6CGBJ5LI","short_pith_number":"pith:RQKUTSSD","schema_version":"1.0","canonical_sha256":"8c1549ca43e4e70dcf7b30fc23053d5a2e5249d80cb614d2344264d0ce8d0ec5","source":{"kind":"arxiv","id":"2305.14720","version":2},"attestation_state":"computed","paper":{"title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongxu Li, Junnan Li, Steven C.H. Hoi","submitted_at":"2023-05-24T04:51:04Z","abstract_excerpt":"Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encod"},"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":"2305.14720","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T04:51:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac11998bdfe6576b53d72b2eeaaa1230aca46f034ea37830b47f0282b70b868c","abstract_canon_sha256":"78fc436a5e8be4ed0e358930f2160154f22323dbfee4075429090f182ad9d31d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:38.177221Z","signature_b64":"YVZIq1tp6fsysrP3gnmGuDQaNSCtRw1+dB28HkfKoKJXM89KZ+GDH6hfJrm6Rko6D2rFFdJ7pKa1cr1nwWMBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c1549ca43e4e70dcf7b30fc23053d5a2e5249d80cb614d2344264d0ce8d0ec5","last_reissued_at":"2026-07-05T06:23:38.176793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:38.176793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongxu Li, Junnan Li, Steven C.H. Hoi","submitted_at":"2023-05-24T04:51:04Z","abstract_excerpt":"Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14720","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/2305.14720/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":"2305.14720","created_at":"2026-07-05T06:23:38.176850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14720v2","created_at":"2026-07-05T06:23:38.176850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14720","created_at":"2026-07-05T06:23:38.176850+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQKUTSSD4TTQ","created_at":"2026-07-05T06:23:38.176850+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQKUTSSD4TTQ3T33","created_at":"2026-07-05T06:23:38.176850+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQKUTSSD","created_at":"2026-07-05T06:23:38.176850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22469","citing_title":"MaSC: A Masked Similarity Metric for Evaluating Concept-Driven Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23690","citing_title":"SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07940","citing_title":"Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13863","citing_title":"PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQKUTSSD4TTQ3T33GD6CGBJ5LI","json":"https://pith.science/pith/RQKUTSSD4TTQ3T33GD6CGBJ5LI.json","graph_json":"https://pith.science/api/pith-number/RQKUTSSD4TTQ3T33GD6CGBJ5LI/graph.json","events_json":"https://pith.science/api/pith-number/RQKUTSSD4TTQ3T33GD6CGBJ5LI/events.json","paper":"https://pith.science/paper/RQKUTSSD"},"agent_actions":{"view_html":"https://pith.science/pith/RQKUTSSD4TTQ3T33GD6CGBJ5LI","download_json":"https://pith.science/pith/RQKUTSSD4TTQ3T33GD6CGBJ5LI.json","view_paper":"https://pith.science/paper/RQKUTSSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14720&json=true","fetch_graph":"https://pith.science/api/pith-number/RQKUTSSD4TTQ3T33GD6CGBJ5LI/graph.json","fetch_events":"https://pith.science/api/pith-number/RQKUTSSD4TTQ3T33GD6CGBJ5LI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQKUTSSD4TTQ3T33GD6CGBJ5LI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQKUTSSD4TTQ3T33GD6CGBJ5LI/action/storage_attestation","attest_author":"https://pith.science/pith/RQKUTSSD4TTQ3T33GD6CGBJ5LI/action/author_attestation","sign_citation":"https://pith.science/pith/RQKUTSSD4TTQ3T33GD6CGBJ5LI/action/citation_signature","submit_replication":"https://pith.science/pith/RQKUTSSD4TTQ3T33GD6CGBJ5LI/action/replication_record"}},"created_at":"2026-07-05T06:23:38.176850+00:00","updated_at":"2026-07-05T06:23:38.176850+00:00"}