{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MOZ4BJ4CC3HARFIPWRBC7Q5NUS","short_pith_number":"pith:MOZ4BJ4C","schema_version":"1.0","canonical_sha256":"63b3c0a78216ce08950fb4422fc3ada489f5b34b40075d3a5a1c330be6cf5014","source":{"kind":"arxiv","id":"2403.13535","version":2},"attestation_state":"computed","paper":{"title":"IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Guo, Jiankang Deng, Siying Cui, Xiang An, Xinyu Wei, Yongle Zhao, Ziyong Feng","submitted_at":"2024-03-20T12:13:04Z","abstract_excerpt":"Leveraging Stable Diffusion for the generation of personalized portraits has emerged as a powerful and noteworthy tool, enabling users to create high-fidelity, custom character avatars based on their specific prompts. However, existing personalization methods face challenges, including test-time fine-tuning, the requirement of multiple input images, low preservation of identity, and limited diversity in generated outcomes. To overcome these challenges, we introduce IDAdapter, a tuning-free approach that enhances the diversity and identity preservation in personalized image generation from a si"},"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":"2403.13535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T12:13:04Z","cross_cats_sorted":[],"title_canon_sha256":"f92c12f704f9592eb728e797b2d1c43dc51a56a077d1399141a9f6650d605308","abstract_canon_sha256":"d9f743ca4d9406eed9121a80aa2faec10abd1b7689b2240ae0868fd419a626e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:50.097806Z","signature_b64":"ykYQ/ckinuftz9DKJOH4/TfQy5Qvvaw7AK35KBQQ189lY2CFjOia92EmvM3FSND1xO5e2yZcokuvkNMeELLjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b3c0a78216ce08950fb4422fc3ada489f5b34b40075d3a5a1c330be6cf5014","last_reissued_at":"2026-07-05T07:58:50.097238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:50.097238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Guo, Jiankang Deng, Siying Cui, Xiang An, Xinyu Wei, Yongle Zhao, Ziyong Feng","submitted_at":"2024-03-20T12:13:04Z","abstract_excerpt":"Leveraging Stable Diffusion for the generation of personalized portraits has emerged as a powerful and noteworthy tool, enabling users to create high-fidelity, custom character avatars based on their specific prompts. However, existing personalization methods face challenges, including test-time fine-tuning, the requirement of multiple input images, low preservation of identity, and limited diversity in generated outcomes. To overcome these challenges, we introduce IDAdapter, a tuning-free approach that enhances the diversity and identity preservation in personalized image generation from a si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13535","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/2403.13535/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":"2403.13535","created_at":"2026-07-05T07:58:50.097295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13535v2","created_at":"2026-07-05T07:58:50.097295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13535","created_at":"2026-07-05T07:58:50.097295+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOZ4BJ4CC3HA","created_at":"2026-07-05T07:58:50.097295+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOZ4BJ4CC3HARFIP","created_at":"2026-07-05T07:58:50.097295+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOZ4BJ4C","created_at":"2026-07-05T07:58:50.097295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02129","citing_title":"Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOZ4BJ4CC3HARFIPWRBC7Q5NUS","json":"https://pith.science/pith/MOZ4BJ4CC3HARFIPWRBC7Q5NUS.json","graph_json":"https://pith.science/api/pith-number/MOZ4BJ4CC3HARFIPWRBC7Q5NUS/graph.json","events_json":"https://pith.science/api/pith-number/MOZ4BJ4CC3HARFIPWRBC7Q5NUS/events.json","paper":"https://pith.science/paper/MOZ4BJ4C"},"agent_actions":{"view_html":"https://pith.science/pith/MOZ4BJ4CC3HARFIPWRBC7Q5NUS","download_json":"https://pith.science/pith/MOZ4BJ4CC3HARFIPWRBC7Q5NUS.json","view_paper":"https://pith.science/paper/MOZ4BJ4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13535&json=true","fetch_graph":"https://pith.science/api/pith-number/MOZ4BJ4CC3HARFIPWRBC7Q5NUS/graph.json","fetch_events":"https://pith.science/api/pith-number/MOZ4BJ4CC3HARFIPWRBC7Q5NUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOZ4BJ4CC3HARFIPWRBC7Q5NUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOZ4BJ4CC3HARFIPWRBC7Q5NUS/action/storage_attestation","attest_author":"https://pith.science/pith/MOZ4BJ4CC3HARFIPWRBC7Q5NUS/action/author_attestation","sign_citation":"https://pith.science/pith/MOZ4BJ4CC3HARFIPWRBC7Q5NUS/action/citation_signature","submit_replication":"https://pith.science/pith/MOZ4BJ4CC3HARFIPWRBC7Q5NUS/action/replication_record"}},"created_at":"2026-07-05T07:58:50.097295+00:00","updated_at":"2026-07-05T07:58:50.097295+00:00"}