{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AXJIB34EN7ISKJ5P6QY65H777X","short_pith_number":"pith:AXJIB34E","schema_version":"1.0","canonical_sha256":"05d280ef846fd12527aff431ee9ffffdf5309b61c5e5cea9d33050bc5be6f0e9","source":{"kind":"arxiv","id":"2212.04488","version":2},"attestation_state":"computed","paper":{"title":"Multi-Concept Customization of Text-to-Image Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bingliang Zhang, Eli Shechtman, Jun-Yan Zhu, Nupur Kumari, Richard Zhang","submitted_at":"2022-12-08T18:57:02Z","abstract_excerpt":"While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to quickly acquire a new concept, given a few examples? Furthermore, can we compose multiple new concepts together? We propose Custom Diffusion, an efficient method for augmenting existing text-to-image models. We find that only optimizing a few parameters in the text-to-image conditioning mechanism is sufficiently powerful to represent new concepts while enab"},"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":"2212.04488","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T18:57:02Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"3ec7a8f88a2e2c333696175463b4827a1ed7a854c7ca6ecc32b4c623943e0c8b","abstract_canon_sha256":"185445262bfa18547472c58ed921a17c0c0c98fab9a571c3fa737a28dde95f4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:56.548159Z","signature_b64":"kQi/k0+K1ITA7HBWN8khfS0Jpcu44ZsnFEMIbOApralUAexrA8kSN9Z/f2kMApO5iCNAEJjRw+QtiA76QczhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05d280ef846fd12527aff431ee9ffffdf5309b61c5e5cea9d33050bc5be6f0e9","last_reissued_at":"2026-07-05T06:21:56.547765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:56.547765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Concept Customization of Text-to-Image Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bingliang Zhang, Eli Shechtman, Jun-Yan Zhu, Nupur Kumari, Richard Zhang","submitted_at":"2022-12-08T18:57:02Z","abstract_excerpt":"While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to quickly acquire a new concept, given a few examples? Furthermore, can we compose multiple new concepts together? We propose Custom Diffusion, an efficient method for augmenting existing text-to-image models. We find that only optimizing a few parameters in the text-to-image conditioning mechanism is sufficiently powerful to represent new concepts while enab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04488","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/2212.04488/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":"2212.04488","created_at":"2026-07-05T06:21:56.547817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04488v2","created_at":"2026-07-05T06:21:56.547817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04488","created_at":"2026-07-05T06:21:56.547817+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXJIB34EN7IS","created_at":"2026-07-05T06:21:56.547817+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXJIB34EN7ISKJ5P","created_at":"2026-07-05T06:21:56.547817+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXJIB34E","created_at":"2026-07-05T06:21:56.547817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07173","citing_title":"Stage-Aware Adaptation and Distribution Calibration for Subject-Driven Personalized Text-to-Image Generation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2411.19182","citing_title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20807","citing_title":"Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23690","citing_title":"SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2302.12192","citing_title":"Aligning Text-to-Image Models using Human Feedback","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13863","citing_title":"PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AXJIB34EN7ISKJ5P6QY65H777X","json":"https://pith.science/pith/AXJIB34EN7ISKJ5P6QY65H777X.json","graph_json":"https://pith.science/api/pith-number/AXJIB34EN7ISKJ5P6QY65H777X/graph.json","events_json":"https://pith.science/api/pith-number/AXJIB34EN7ISKJ5P6QY65H777X/events.json","paper":"https://pith.science/paper/AXJIB34E"},"agent_actions":{"view_html":"https://pith.science/pith/AXJIB34EN7ISKJ5P6QY65H777X","download_json":"https://pith.science/pith/AXJIB34EN7ISKJ5P6QY65H777X.json","view_paper":"https://pith.science/paper/AXJIB34E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04488&json=true","fetch_graph":"https://pith.science/api/pith-number/AXJIB34EN7ISKJ5P6QY65H777X/graph.json","fetch_events":"https://pith.science/api/pith-number/AXJIB34EN7ISKJ5P6QY65H777X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXJIB34EN7ISKJ5P6QY65H777X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXJIB34EN7ISKJ5P6QY65H777X/action/storage_attestation","attest_author":"https://pith.science/pith/AXJIB34EN7ISKJ5P6QY65H777X/action/author_attestation","sign_citation":"https://pith.science/pith/AXJIB34EN7ISKJ5P6QY65H777X/action/citation_signature","submit_replication":"https://pith.science/pith/AXJIB34EN7ISKJ5P6QY65H777X/action/replication_record"}},"created_at":"2026-07-05T06:21:56.547817+00:00","updated_at":"2026-07-05T06:21:56.547817+00:00"}