{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CYX5P2KNXUPWAUPCOVI2NY4FQ7","short_pith_number":"pith:CYX5P2KN","schema_version":"1.0","canonical_sha256":"162fd7e94dbd1f6051e27551a6e38587e44ffa2abfa81a542328291f8180cf2b","source":{"kind":"arxiv","id":"2401.16157","version":1},"attestation_state":"computed","paper":{"title":"Spatial-Aware Latent Initialization for Controllable Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun Zhang, Teng Li, Wenqiang Sun, Zehong Lin","submitted_at":"2024-01-29T13:42:01Z","abstract_excerpt":"Recently, text-to-image diffusion models have demonstrated impressive ability to generate high-quality images conditioned on the textual input. However, these models struggle to accurately adhere to textual instructions regarding spatial layout information. While previous research has primarily focused on aligning cross-attention maps with layout conditions, they overlook the impact of the initialization noise on the layout guidance. To achieve better layout control, we propose leveraging a spatial-aware initialization noise during the denoising process. Specifically, we find that the inverted"},"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":"2401.16157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T13:42:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4e904f781921724d841735ef285ae2c6172b56b1f99ea2a17c3c7d4135a5895a","abstract_canon_sha256":"e25242975e85a45fc242ecda804d972f53a0dd954935a7967229869aaeaf963b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:44.909408Z","signature_b64":"toPXFjM8yXF30djlEUk5yOgYX5uXhRdMn39HdK7sqbgc1TrOt8+JbV6s6CwhGMWUmwO58s9aLDsLJtYXiaMsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"162fd7e94dbd1f6051e27551a6e38587e44ffa2abfa81a542328291f8180cf2b","last_reissued_at":"2026-07-05T07:38:44.908988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:44.908988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial-Aware Latent Initialization for Controllable Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jun Zhang, Teng Li, Wenqiang Sun, Zehong Lin","submitted_at":"2024-01-29T13:42:01Z","abstract_excerpt":"Recently, text-to-image diffusion models have demonstrated impressive ability to generate high-quality images conditioned on the textual input. However, these models struggle to accurately adhere to textual instructions regarding spatial layout information. While previous research has primarily focused on aligning cross-attention maps with layout conditions, they overlook the impact of the initialization noise on the layout guidance. To achieve better layout control, we propose leveraging a spatial-aware initialization noise during the denoising process. Specifically, we find that the inverted"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16157","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/2401.16157/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":"2401.16157","created_at":"2026-07-05T07:38:44.909045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16157v1","created_at":"2026-07-05T07:38:44.909045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16157","created_at":"2026-07-05T07:38:44.909045+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYX5P2KNXUPW","created_at":"2026-07-05T07:38:44.909045+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYX5P2KNXUPWAUPC","created_at":"2026-07-05T07:38:44.909045+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYX5P2KN","created_at":"2026-07-05T07:38:44.909045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15115","citing_title":"Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CYX5P2KNXUPWAUPCOVI2NY4FQ7","json":"https://pith.science/pith/CYX5P2KNXUPWAUPCOVI2NY4FQ7.json","graph_json":"https://pith.science/api/pith-number/CYX5P2KNXUPWAUPCOVI2NY4FQ7/graph.json","events_json":"https://pith.science/api/pith-number/CYX5P2KNXUPWAUPCOVI2NY4FQ7/events.json","paper":"https://pith.science/paper/CYX5P2KN"},"agent_actions":{"view_html":"https://pith.science/pith/CYX5P2KNXUPWAUPCOVI2NY4FQ7","download_json":"https://pith.science/pith/CYX5P2KNXUPWAUPCOVI2NY4FQ7.json","view_paper":"https://pith.science/paper/CYX5P2KN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16157&json=true","fetch_graph":"https://pith.science/api/pith-number/CYX5P2KNXUPWAUPCOVI2NY4FQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/CYX5P2KNXUPWAUPCOVI2NY4FQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYX5P2KNXUPWAUPCOVI2NY4FQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYX5P2KNXUPWAUPCOVI2NY4FQ7/action/storage_attestation","attest_author":"https://pith.science/pith/CYX5P2KNXUPWAUPCOVI2NY4FQ7/action/author_attestation","sign_citation":"https://pith.science/pith/CYX5P2KNXUPWAUPCOVI2NY4FQ7/action/citation_signature","submit_replication":"https://pith.science/pith/CYX5P2KNXUPWAUPCOVI2NY4FQ7/action/replication_record"}},"created_at":"2026-07-05T07:38:44.909045+00:00","updated_at":"2026-07-05T07:38:44.909045+00:00"}