{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CEKRQDCBSEBB3DG2R23UJQS526","short_pith_number":"pith:CEKRQDCB","schema_version":"1.0","canonical_sha256":"1115180c4191021d8cda8eb744c25dd7b96247fbcc652eb437447af0c0b006b4","source":{"kind":"arxiv","id":"2410.13370","version":3},"attestation_state":"computed","paper":{"title":"MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Donghao Zhou, Guangyong Chen, Hao Chen, Jiancheng Huang, Jiaze Wang, Jinbin Bai, Pheng-Ann Heng, Xiaowei Hu","submitted_at":"2024-10-17T09:22:53Z","abstract_excerpt":"Text-to-image diffusion models can generate high-quality images but lack fine-grained control of visual concepts, limiting their creativity. Thus, we introduce component-controllable personalization, a new task that enables users to customize and reconfigure individual components within concepts. This task faces two challenges: semantic pollution, where undesired elements disrupt the target concept, and semantic imbalance, which causes disproportionate learning of the target concept and component. To address these, we design MagicTailor, a framework that uses Dynamic Masked Degradation to adap"},"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":"2410.13370","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T09:22:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fa0dfcaa3e28dc13472c81b230e492336aa9b49218c4418781b7ab84496a3035","abstract_canon_sha256":"4e842350a98862c4076c6f142ab597f7a47326c38dd6fd90f409c278c7513942"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:24.279616Z","signature_b64":"3wxMt+cixR4zhPtnh4dgsnCh+wK4uOf6VpoF+3Voucamv3Dzly/e4xRcRvsJ8sAn4CDWJRjUkKAPW0SBJHPZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1115180c4191021d8cda8eb744c25dd7b96247fbcc652eb437447af0c0b006b4","last_reissued_at":"2026-07-05T11:06:24.279055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:24.279055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Donghao Zhou, Guangyong Chen, Hao Chen, Jiancheng Huang, Jiaze Wang, Jinbin Bai, Pheng-Ann Heng, Xiaowei Hu","submitted_at":"2024-10-17T09:22:53Z","abstract_excerpt":"Text-to-image diffusion models can generate high-quality images but lack fine-grained control of visual concepts, limiting their creativity. Thus, we introduce component-controllable personalization, a new task that enables users to customize and reconfigure individual components within concepts. This task faces two challenges: semantic pollution, where undesired elements disrupt the target concept, and semantic imbalance, which causes disproportionate learning of the target concept and component. To address these, we design MagicTailor, a framework that uses Dynamic Masked Degradation to adap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13370","kind":"arxiv","version":3},"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/2410.13370/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":"2410.13370","created_at":"2026-07-05T11:06:24.279121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13370v3","created_at":"2026-07-05T11:06:24.279121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13370","created_at":"2026-07-05T11:06:24.279121+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEKRQDCBSEBB","created_at":"2026-07-05T11:06:24.279121+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEKRQDCBSEBB3DG2","created_at":"2026-07-05T11:06:24.279121+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEKRQDCB","created_at":"2026-07-05T11:06:24.279121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.12598","citing_title":"Setting the Stage: Text-Driven Scene-Consistent Image Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22160","citing_title":"Screen, Cache, and Match: A Training-Free Causality-Consistent Reference Frame Framework for Human Animation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02210","citing_title":"HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11804","citing_title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEKRQDCBSEBB3DG2R23UJQS526","json":"https://pith.science/pith/CEKRQDCBSEBB3DG2R23UJQS526.json","graph_json":"https://pith.science/api/pith-number/CEKRQDCBSEBB3DG2R23UJQS526/graph.json","events_json":"https://pith.science/api/pith-number/CEKRQDCBSEBB3DG2R23UJQS526/events.json","paper":"https://pith.science/paper/CEKRQDCB"},"agent_actions":{"view_html":"https://pith.science/pith/CEKRQDCBSEBB3DG2R23UJQS526","download_json":"https://pith.science/pith/CEKRQDCBSEBB3DG2R23UJQS526.json","view_paper":"https://pith.science/paper/CEKRQDCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13370&json=true","fetch_graph":"https://pith.science/api/pith-number/CEKRQDCBSEBB3DG2R23UJQS526/graph.json","fetch_events":"https://pith.science/api/pith-number/CEKRQDCBSEBB3DG2R23UJQS526/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEKRQDCBSEBB3DG2R23UJQS526/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEKRQDCBSEBB3DG2R23UJQS526/action/storage_attestation","attest_author":"https://pith.science/pith/CEKRQDCBSEBB3DG2R23UJQS526/action/author_attestation","sign_citation":"https://pith.science/pith/CEKRQDCBSEBB3DG2R23UJQS526/action/citation_signature","submit_replication":"https://pith.science/pith/CEKRQDCBSEBB3DG2R23UJQS526/action/replication_record"}},"created_at":"2026-07-05T11:06:24.279121+00:00","updated_at":"2026-07-05T11:06:24.279121+00:00"}