{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UIL4FKKBFISB2X65DAKM3QPUV2","short_pith_number":"pith:UIL4FKKB","schema_version":"1.0","canonical_sha256":"a217c2a9412a241d5fdd1814cdc1f4ae92823efe1bfe3f87c2565bc932b9bbbe","source":{"kind":"arxiv","id":"2312.08768","version":3},"attestation_state":"computed","paper":{"title":"Local Conditional Controlling for Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxi Wu, Hengjia Li, Liang Peng, Qinglin Lu, Wei Liu, Wei Zhao, Xiaofei He, Yang Yang, Yao Chen, Yibo Zhao, Zekai Luo, Zheng Yang","submitted_at":"2023-12-14T09:31:33Z","abstract_excerpt":"Diffusion models have exhibited impressive prowess in the text-to-image task. Recent methods add image-level structure controls, e.g., edge and depth maps, to manipulate the generation process together with text prompts to obtain desired images. This controlling process is globally operated on the entire image, which limits the flexibility of control regions. In this paper, we explore a novel and practical task setting: local control. It focuses on controlling specific local region according to user-defined image conditions, while the remaining regions are only conditioned by the original text"},"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":"2312.08768","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T09:31:33Z","cross_cats_sorted":[],"title_canon_sha256":"5dbb991c8ba0bfa139c8733e978706d8fb3881cc6b88f8f355aa2cb72efdc617","abstract_canon_sha256":"58173cc3d4f879230a90b035af04b6183256e80c7a37147761b401f3cfeaa592"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:53.867281Z","signature_b64":"12UdYIwB6XcfrdT3c4UF4i3o+XrjlQl8NLxlh+cvFAeXdaU23AChaIJwwa9481csVpMcMgWs9InhtvQoqQWjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a217c2a9412a241d5fdd1814cdc1f4ae92823efe1bfe3f87c2565bc932b9bbbe","last_reissued_at":"2026-07-05T08:57:53.866808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:53.866808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Conditional Controlling for Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxi Wu, Hengjia Li, Liang Peng, Qinglin Lu, Wei Liu, Wei Zhao, Xiaofei He, Yang Yang, Yao Chen, Yibo Zhao, Zekai Luo, Zheng Yang","submitted_at":"2023-12-14T09:31:33Z","abstract_excerpt":"Diffusion models have exhibited impressive prowess in the text-to-image task. Recent methods add image-level structure controls, e.g., edge and depth maps, to manipulate the generation process together with text prompts to obtain desired images. This controlling process is globally operated on the entire image, which limits the flexibility of control regions. In this paper, we explore a novel and practical task setting: local control. It focuses on controlling specific local region according to user-defined image conditions, while the remaining regions are only conditioned by the original text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08768","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/2312.08768/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":"2312.08768","created_at":"2026-07-05T08:57:53.866866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08768v3","created_at":"2026-07-05T08:57:53.866866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08768","created_at":"2026-07-05T08:57:53.866866+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIL4FKKBFISB","created_at":"2026-07-05T08:57:53.866866+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIL4FKKBFISB2X65","created_at":"2026-07-05T08:57:53.866866+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIL4FKKB","created_at":"2026-07-05T08:57:53.866866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24086","citing_title":"ComposeAnything: Composite Object Priors for Text-to-Image Generation","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UIL4FKKBFISB2X65DAKM3QPUV2","json":"https://pith.science/pith/UIL4FKKBFISB2X65DAKM3QPUV2.json","graph_json":"https://pith.science/api/pith-number/UIL4FKKBFISB2X65DAKM3QPUV2/graph.json","events_json":"https://pith.science/api/pith-number/UIL4FKKBFISB2X65DAKM3QPUV2/events.json","paper":"https://pith.science/paper/UIL4FKKB"},"agent_actions":{"view_html":"https://pith.science/pith/UIL4FKKBFISB2X65DAKM3QPUV2","download_json":"https://pith.science/pith/UIL4FKKBFISB2X65DAKM3QPUV2.json","view_paper":"https://pith.science/paper/UIL4FKKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08768&json=true","fetch_graph":"https://pith.science/api/pith-number/UIL4FKKBFISB2X65DAKM3QPUV2/graph.json","fetch_events":"https://pith.science/api/pith-number/UIL4FKKBFISB2X65DAKM3QPUV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIL4FKKBFISB2X65DAKM3QPUV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIL4FKKBFISB2X65DAKM3QPUV2/action/storage_attestation","attest_author":"https://pith.science/pith/UIL4FKKBFISB2X65DAKM3QPUV2/action/author_attestation","sign_citation":"https://pith.science/pith/UIL4FKKBFISB2X65DAKM3QPUV2/action/citation_signature","submit_replication":"https://pith.science/pith/UIL4FKKBFISB2X65DAKM3QPUV2/action/replication_record"}},"created_at":"2026-07-05T08:57:53.866866+00:00","updated_at":"2026-07-05T08:57:53.866866+00:00"}