{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:APBPJJKWMNBZFHAESYLOKLF7IV","short_pith_number":"pith:APBPJJKW","schema_version":"1.0","canonical_sha256":"03c2f4a5566343929c049616e52cbf4563f5a6e9efc9f0d480a5d2dec0d60f2e","source":{"kind":"arxiv","id":"2406.06258","version":2},"attestation_state":"computed","paper":{"title":"Tuning-Free Visual Customization via View Iterative Self-Attention Control","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenghao Gu, Shuzhao Xie, Weixiang Zhang, Xiaojie Li, Yunpeng Bai, Zhi Wang","submitted_at":"2024-06-10T13:41:10Z","abstract_excerpt":"Fine-Tuning Diffusion Models enable a wide range of personalized generation and editing applications on diverse visual modalities. While Low-Rank Adaptation (LoRA) accelerates the fine-tuning process, it still requires multiple reference images and time-consuming training, which constrains its scalability for large-scale and real-time applications. In this paper, we propose \\textit{View Iterative Self-Attention Control (VisCtrl)} to tackle this challenge. Specifically, VisCtrl is a training-free method that injects the appearance and structure of a user-specified subject into another subject i"},"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":"2406.06258","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T13:41:10Z","cross_cats_sorted":[],"title_canon_sha256":"e8bf44e035c3a487d42e220d490acebd50008dc8f41c146138a8e3b3677b7afd","abstract_canon_sha256":"cb9224eb8e86cc1db206cf76dc18403bb99a6f9ccf68d25c3ac89031df02f1d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:14.495913Z","signature_b64":"4q6oT22pxx0rwtoOPw9C2LOo/VSle0KM/DIuB+CDnmMTL4H1dOvTWwYae6if6/0985Bt0Ggr+XvbCbXynVe/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03c2f4a5566343929c049616e52cbf4563f5a6e9efc9f0d480a5d2dec0d60f2e","last_reissued_at":"2026-07-05T08:30:14.495468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:14.495468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tuning-Free Visual Customization via View Iterative Self-Attention Control","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenghao Gu, Shuzhao Xie, Weixiang Zhang, Xiaojie Li, Yunpeng Bai, Zhi Wang","submitted_at":"2024-06-10T13:41:10Z","abstract_excerpt":"Fine-Tuning Diffusion Models enable a wide range of personalized generation and editing applications on diverse visual modalities. While Low-Rank Adaptation (LoRA) accelerates the fine-tuning process, it still requires multiple reference images and time-consuming training, which constrains its scalability for large-scale and real-time applications. In this paper, we propose \\textit{View Iterative Self-Attention Control (VisCtrl)} to tackle this challenge. Specifically, VisCtrl is a training-free method that injects the appearance and structure of a user-specified subject into another subject i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06258","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/2406.06258/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":"2406.06258","created_at":"2026-07-05T08:30:14.495532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06258v2","created_at":"2026-07-05T08:30:14.495532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06258","created_at":"2026-07-05T08:30:14.495532+00:00"},{"alias_kind":"pith_short_12","alias_value":"APBPJJKWMNBZ","created_at":"2026-07-05T08:30:14.495532+00:00"},{"alias_kind":"pith_short_16","alias_value":"APBPJJKWMNBZFHAE","created_at":"2026-07-05T08:30:14.495532+00:00"},{"alias_kind":"pith_short_8","alias_value":"APBPJJKW","created_at":"2026-07-05T08:30:14.495532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21452","citing_title":"Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional Training","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APBPJJKWMNBZFHAESYLOKLF7IV","json":"https://pith.science/pith/APBPJJKWMNBZFHAESYLOKLF7IV.json","graph_json":"https://pith.science/api/pith-number/APBPJJKWMNBZFHAESYLOKLF7IV/graph.json","events_json":"https://pith.science/api/pith-number/APBPJJKWMNBZFHAESYLOKLF7IV/events.json","paper":"https://pith.science/paper/APBPJJKW"},"agent_actions":{"view_html":"https://pith.science/pith/APBPJJKWMNBZFHAESYLOKLF7IV","download_json":"https://pith.science/pith/APBPJJKWMNBZFHAESYLOKLF7IV.json","view_paper":"https://pith.science/paper/APBPJJKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06258&json=true","fetch_graph":"https://pith.science/api/pith-number/APBPJJKWMNBZFHAESYLOKLF7IV/graph.json","fetch_events":"https://pith.science/api/pith-number/APBPJJKWMNBZFHAESYLOKLF7IV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APBPJJKWMNBZFHAESYLOKLF7IV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APBPJJKWMNBZFHAESYLOKLF7IV/action/storage_attestation","attest_author":"https://pith.science/pith/APBPJJKWMNBZFHAESYLOKLF7IV/action/author_attestation","sign_citation":"https://pith.science/pith/APBPJJKWMNBZFHAESYLOKLF7IV/action/citation_signature","submit_replication":"https://pith.science/pith/APBPJJKWMNBZFHAESYLOKLF7IV/action/replication_record"}},"created_at":"2026-07-05T08:30:14.495532+00:00","updated_at":"2026-07-05T08:30:14.495532+00:00"}