{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YCDUKKOCEGI5B5DS2TAVG7MRQI","short_pith_number":"pith:YCDUKKOC","schema_version":"1.0","canonical_sha256":"c0874529c22191d0f472d4c1537d91821c2cd04ea1e0bcb8b52088f9a5af77d6","source":{"kind":"arxiv","id":"2406.05000","version":1},"attestation_state":"computed","paper":{"title":"AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoquan Zhao, Feize Wu, Fu Lee Wang, Jian Yin, Lianyu Pang, Qing Li, Xudong Mao","submitted_at":"2024-06-07T15:12:26Z","abstract_excerpt":"Recent advances in text-to-image models have enabled high-quality personalized image synthesis of user-provided concepts with flexible textual control. In this work, we analyze the limitations of two primary techniques in text-to-image personalization: Textual Inversion and DreamBooth. When integrating the learned concept into new prompts, Textual Inversion tends to overfit the concept, while DreamBooth often overlooks it. We attribute these issues to the incorrect learning of the embedding alignment for the concept. We introduce AttnDreamBooth, a novel approach that addresses these issues by "},"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":"2406.05000","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T15:12:26Z","cross_cats_sorted":[],"title_canon_sha256":"dd09e2961e04318a86df27d874e92282b65b6e8490af14be229f2995c955e7e3","abstract_canon_sha256":"e17c95556bcf0025e5556d707282a1637b095d2eee16aeb60663d9f3be80877b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:52.095113Z","signature_b64":"DokNoZ9SJPt12yBYSSBmrvqI/vNSHRMGwipjp9PI+BPnBqm1IqIKw9bhU9U0Jl6gw7WL4gDbOxafjvuNC7LOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0874529c22191d0f472d4c1537d91821c2cd04ea1e0bcb8b52088f9a5af77d6","last_reissued_at":"2026-07-05T08:28:52.094638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:52.094638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoquan Zhao, Feize Wu, Fu Lee Wang, Jian Yin, Lianyu Pang, Qing Li, Xudong Mao","submitted_at":"2024-06-07T15:12:26Z","abstract_excerpt":"Recent advances in text-to-image models have enabled high-quality personalized image synthesis of user-provided concepts with flexible textual control. In this work, we analyze the limitations of two primary techniques in text-to-image personalization: Textual Inversion and DreamBooth. When integrating the learned concept into new prompts, Textual Inversion tends to overfit the concept, while DreamBooth often overlooks it. We attribute these issues to the incorrect learning of the embedding alignment for the concept. We introduce AttnDreamBooth, a novel approach that addresses these issues by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05000","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/2406.05000/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":"2406.05000","created_at":"2026-07-05T08:28:52.094698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05000v1","created_at":"2026-07-05T08:28:52.094698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05000","created_at":"2026-07-05T08:28:52.094698+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCDUKKOCEGI5","created_at":"2026-07-05T08:28:52.094698+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCDUKKOCEGI5B5DS","created_at":"2026-07-05T08:28:52.094698+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCDUKKOC","created_at":"2026-07-05T08:28:52.094698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09064","citing_title":"StyleBlend: Enhancing Style-Specific Content Creation in Text-to-Image Diffusion Models","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCDUKKOCEGI5B5DS2TAVG7MRQI","json":"https://pith.science/pith/YCDUKKOCEGI5B5DS2TAVG7MRQI.json","graph_json":"https://pith.science/api/pith-number/YCDUKKOCEGI5B5DS2TAVG7MRQI/graph.json","events_json":"https://pith.science/api/pith-number/YCDUKKOCEGI5B5DS2TAVG7MRQI/events.json","paper":"https://pith.science/paper/YCDUKKOC"},"agent_actions":{"view_html":"https://pith.science/pith/YCDUKKOCEGI5B5DS2TAVG7MRQI","download_json":"https://pith.science/pith/YCDUKKOCEGI5B5DS2TAVG7MRQI.json","view_paper":"https://pith.science/paper/YCDUKKOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05000&json=true","fetch_graph":"https://pith.science/api/pith-number/YCDUKKOCEGI5B5DS2TAVG7MRQI/graph.json","fetch_events":"https://pith.science/api/pith-number/YCDUKKOCEGI5B5DS2TAVG7MRQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCDUKKOCEGI5B5DS2TAVG7MRQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCDUKKOCEGI5B5DS2TAVG7MRQI/action/storage_attestation","attest_author":"https://pith.science/pith/YCDUKKOCEGI5B5DS2TAVG7MRQI/action/author_attestation","sign_citation":"https://pith.science/pith/YCDUKKOCEGI5B5DS2TAVG7MRQI/action/citation_signature","submit_replication":"https://pith.science/pith/YCDUKKOCEGI5B5DS2TAVG7MRQI/action/replication_record"}},"created_at":"2026-07-05T08:28:52.094698+00:00","updated_at":"2026-07-05T08:28:52.094698+00:00"}