{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YVTLCXQPZ664XYQB3GOMVL7BJC","short_pith_number":"pith:YVTLCXQP","schema_version":"1.0","canonical_sha256":"c566b15e0fcfbdcbe201d99ccaafe148a2fd2cb03a72402ae8f85c7efd16c4a1","source":{"kind":"arxiv","id":"2404.06451","version":1},"attestation_state":"computed","paper":{"title":"SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ming Liu, Peiran Ren, Wangmeng Zuo, Xianhui Lin, Xiaoyu Liu, Xuansong Xie, Yuxiang Wei","submitted_at":"2024-04-09T16:53:43Z","abstract_excerpt":"Human visual imagination usually begins with analogies or rough sketches. For example, given an image with a girl playing guitar before a building, one may analogously imagine how it seems like if Iron Man playing guitar before Pyramid in Egypt. Nonetheless, visual condition may not be precisely aligned with the imaginary result indicated by text prompt, and existing layout-controllable text-to-image (T2I) generation models is prone to producing degraded generated results with obvious artifacts. To address this issue, we present a novel T2I generation method dubbed SmartControl, which is desig"},"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":"2404.06451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T16:53:43Z","cross_cats_sorted":[],"title_canon_sha256":"078594801d88f68038cbb74a2b594c67c4b4740bf83d5c206dd7f093cb822346","abstract_canon_sha256":"28034cf3370a84ce3dd521441987e9e94343d45b3555ef219c01c349d9cb374f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:09.236212Z","signature_b64":"nJpY9qeHFykIT/7SwtTUuEcAXLtOtCxrFRX8+r1E+HrMxf5Z5jlTx4uSN2v0z3DXhi1Cn4qk8R8eZR9UGeN3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c566b15e0fcfbdcbe201d99ccaafe148a2fd2cb03a72402ae8f85c7efd16c4a1","last_reissued_at":"2026-07-05T08:06:09.235791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:09.235791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ming Liu, Peiran Ren, Wangmeng Zuo, Xianhui Lin, Xiaoyu Liu, Xuansong Xie, Yuxiang Wei","submitted_at":"2024-04-09T16:53:43Z","abstract_excerpt":"Human visual imagination usually begins with analogies or rough sketches. For example, given an image with a girl playing guitar before a building, one may analogously imagine how it seems like if Iron Man playing guitar before Pyramid in Egypt. Nonetheless, visual condition may not be precisely aligned with the imaginary result indicated by text prompt, and existing layout-controllable text-to-image (T2I) generation models is prone to producing degraded generated results with obvious artifacts. To address this issue, we present a novel T2I generation method dubbed SmartControl, which is desig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06451","kind":"arxiv","version":1},"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/2404.06451/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":"2404.06451","created_at":"2026-07-05T08:06:09.235861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06451v1","created_at":"2026-07-05T08:06:09.235861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06451","created_at":"2026-07-05T08:06:09.235861+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVTLCXQPZ664","created_at":"2026-07-05T08:06:09.235861+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVTLCXQPZ664XYQB","created_at":"2026-07-05T08:06:09.235861+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVTLCXQP","created_at":"2026-07-05T08:06:09.235861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.14209","citing_title":"ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVTLCXQPZ664XYQB3GOMVL7BJC","json":"https://pith.science/pith/YVTLCXQPZ664XYQB3GOMVL7BJC.json","graph_json":"https://pith.science/api/pith-number/YVTLCXQPZ664XYQB3GOMVL7BJC/graph.json","events_json":"https://pith.science/api/pith-number/YVTLCXQPZ664XYQB3GOMVL7BJC/events.json","paper":"https://pith.science/paper/YVTLCXQP"},"agent_actions":{"view_html":"https://pith.science/pith/YVTLCXQPZ664XYQB3GOMVL7BJC","download_json":"https://pith.science/pith/YVTLCXQPZ664XYQB3GOMVL7BJC.json","view_paper":"https://pith.science/paper/YVTLCXQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06451&json=true","fetch_graph":"https://pith.science/api/pith-number/YVTLCXQPZ664XYQB3GOMVL7BJC/graph.json","fetch_events":"https://pith.science/api/pith-number/YVTLCXQPZ664XYQB3GOMVL7BJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVTLCXQPZ664XYQB3GOMVL7BJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVTLCXQPZ664XYQB3GOMVL7BJC/action/storage_attestation","attest_author":"https://pith.science/pith/YVTLCXQPZ664XYQB3GOMVL7BJC/action/author_attestation","sign_citation":"https://pith.science/pith/YVTLCXQPZ664XYQB3GOMVL7BJC/action/citation_signature","submit_replication":"https://pith.science/pith/YVTLCXQPZ664XYQB3GOMVL7BJC/action/replication_record"}},"created_at":"2026-07-05T08:06:09.235861+00:00","updated_at":"2026-07-05T08:06:09.235861+00:00"}