{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ESO3T4WGCDCOS6HRI36A6C26AS","short_pith_number":"pith:ESO3T4WG","schema_version":"1.0","canonical_sha256":"249db9f2c610c4e978f146fc0f0b5e0480e483340fed07e4015fd473a65ec924","source":{"kind":"arxiv","id":"2311.12342","version":3},"attestation_state":"computed","paper":{"title":"LoCo: Locally Constrained Training-Free Layout-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Li, Peiang Zhao, Ruiyang Jin, S. Kevin Zhou","submitted_at":"2023-11-21T04:28:12Z","abstract_excerpt":"Recent text-to-image diffusion models have reached an unprecedented level in generating high-quality images. However, their exclusive reliance on textual prompts often falls short in precise control of image compositions. In this paper, we propose LoCo, a training-free approach for layout-to-image Synthesis that excels in producing high-quality images aligned with both textual prompts and layout instructions. Specifically, we introduce a Localized Attention Constraint (LAC), leveraging semantic affinity between pixels in self-attention maps to create precise representations of desired objects "},"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":"2311.12342","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T04:28:12Z","cross_cats_sorted":[],"title_canon_sha256":"cf36db8fe7dd1c38121bef4124a1b9f7ae7aa102f09ebc4a2cc059bbc1a898d0","abstract_canon_sha256":"2291658ce529fac2afabfe00997025abfaaac960bc9a6df667a0fe988e099e1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:38.363638Z","signature_b64":"+M4CQhdBogeufOSD+juxGNGjbhuZ8qjJXX8R4b/6LJG/M41VxDc6dxfOYEH88s9OIaJROiS7ErPo9hivePZPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"249db9f2c610c4e978f146fc0f0b5e0480e483340fed07e4015fd473a65ec924","last_reissued_at":"2026-07-05T08:00:38.363027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:38.363027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoCo: Locally Constrained Training-Free Layout-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Li, Peiang Zhao, Ruiyang Jin, S. Kevin Zhou","submitted_at":"2023-11-21T04:28:12Z","abstract_excerpt":"Recent text-to-image diffusion models have reached an unprecedented level in generating high-quality images. However, their exclusive reliance on textual prompts often falls short in precise control of image compositions. In this paper, we propose LoCo, a training-free approach for layout-to-image Synthesis that excels in producing high-quality images aligned with both textual prompts and layout instructions. Specifically, we introduce a Localized Attention Constraint (LAC), leveraging semantic affinity between pixels in self-attention maps to create precise representations of desired objects "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12342","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/2311.12342/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":"2311.12342","created_at":"2026-07-05T08:00:38.363101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12342v3","created_at":"2026-07-05T08:00:38.363101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12342","created_at":"2026-07-05T08:00:38.363101+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESO3T4WGCDCO","created_at":"2026-07-05T08:00:38.363101+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESO3T4WGCDCOS6HR","created_at":"2026-07-05T08:00:38.363101+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESO3T4WG","created_at":"2026-07-05T08:00:38.363101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESO3T4WGCDCOS6HRI36A6C26AS","json":"https://pith.science/pith/ESO3T4WGCDCOS6HRI36A6C26AS.json","graph_json":"https://pith.science/api/pith-number/ESO3T4WGCDCOS6HRI36A6C26AS/graph.json","events_json":"https://pith.science/api/pith-number/ESO3T4WGCDCOS6HRI36A6C26AS/events.json","paper":"https://pith.science/paper/ESO3T4WG"},"agent_actions":{"view_html":"https://pith.science/pith/ESO3T4WGCDCOS6HRI36A6C26AS","download_json":"https://pith.science/pith/ESO3T4WGCDCOS6HRI36A6C26AS.json","view_paper":"https://pith.science/paper/ESO3T4WG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12342&json=true","fetch_graph":"https://pith.science/api/pith-number/ESO3T4WGCDCOS6HRI36A6C26AS/graph.json","fetch_events":"https://pith.science/api/pith-number/ESO3T4WGCDCOS6HRI36A6C26AS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESO3T4WGCDCOS6HRI36A6C26AS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESO3T4WGCDCOS6HRI36A6C26AS/action/storage_attestation","attest_author":"https://pith.science/pith/ESO3T4WGCDCOS6HRI36A6C26AS/action/author_attestation","sign_citation":"https://pith.science/pith/ESO3T4WGCDCOS6HRI36A6C26AS/action/citation_signature","submit_replication":"https://pith.science/pith/ESO3T4WGCDCOS6HRI36A6C26AS/action/replication_record"}},"created_at":"2026-07-05T08:00:38.363101+00:00","updated_at":"2026-07-05T08:00:38.363101+00:00"}