{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JNNX55AWD3K5MQSIBJOUS3T65F","short_pith_number":"pith:JNNX55AW","schema_version":"1.0","canonical_sha256":"4b5b7ef4161ed5d642480a5d496e7ee94cbcaf5033f583e2cb690e60f847bc46","source":{"kind":"arxiv","id":"2312.02133","version":2},"attestation_state":"computed","paper":{"title":"Style Aligned Image Generation via Shared Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amir Hertz, Andrey Voynov, Daniel Cohen-Or, Shlomi Fruchter","submitted_at":"2023-12-04T18:55:35Z","abstract_excerpt":"Large-scale Text-to-Image (T2I) models have rapidly gained prominence across creative fields, generating visually compelling outputs from textual prompts. However, controlling these models to ensure consistent style remains challenging, with existing methods necessitating fine-tuning and manual intervention to disentangle content and style. In this paper, we introduce StyleAligned, a novel technique designed to establish style alignment among a series of generated images. By employing minimal `attention sharing' during the diffusion process, our method maintains style consistency across images"},"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":"2312.02133","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:55:35Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"f384494aeb5860c94e4c29ab3402175fb1440392fcf0e8c84cd17f648dd7e2cb","abstract_canon_sha256":"b0e70a31a8b354ae03446b20074e6ff1729efa3375d0590f7fc82b6d4b49edcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:25.365644Z","signature_b64":"9nvKAA0Yc41Do9phQCuxa4UMaZ0s9QKGWhipS0kXCMwvUN8lM572JIO0MswAOHdItitwtuGmvaEJa5A1xC4zDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b5b7ef4161ed5d642480a5d496e7ee94cbcaf5033f583e2cb690e60f847bc46","last_reissued_at":"2026-07-05T07:32:25.365166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:25.365166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Style Aligned Image Generation via Shared Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amir Hertz, Andrey Voynov, Daniel Cohen-Or, Shlomi Fruchter","submitted_at":"2023-12-04T18:55:35Z","abstract_excerpt":"Large-scale Text-to-Image (T2I) models have rapidly gained prominence across creative fields, generating visually compelling outputs from textual prompts. However, controlling these models to ensure consistent style remains challenging, with existing methods necessitating fine-tuning and manual intervention to disentangle content and style. In this paper, we introduce StyleAligned, a novel technique designed to establish style alignment among a series of generated images. By employing minimal `attention sharing' during the diffusion process, our method maintains style consistency across images"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02133","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/2312.02133/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":"2312.02133","created_at":"2026-07-05T07:32:25.365221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02133v2","created_at":"2026-07-05T07:32:25.365221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02133","created_at":"2026-07-05T07:32:25.365221+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNNX55AWD3K5","created_at":"2026-07-05T07:32:25.365221+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNNX55AWD3K5MQSI","created_at":"2026-07-05T07:32:25.365221+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNNX55AW","created_at":"2026-07-05T07:32:25.365221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23679","citing_title":"Semantic Browsing: Controllable Diversity for Image Generation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08364","citing_title":"MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNNX55AWD3K5MQSIBJOUS3T65F","json":"https://pith.science/pith/JNNX55AWD3K5MQSIBJOUS3T65F.json","graph_json":"https://pith.science/api/pith-number/JNNX55AWD3K5MQSIBJOUS3T65F/graph.json","events_json":"https://pith.science/api/pith-number/JNNX55AWD3K5MQSIBJOUS3T65F/events.json","paper":"https://pith.science/paper/JNNX55AW"},"agent_actions":{"view_html":"https://pith.science/pith/JNNX55AWD3K5MQSIBJOUS3T65F","download_json":"https://pith.science/pith/JNNX55AWD3K5MQSIBJOUS3T65F.json","view_paper":"https://pith.science/paper/JNNX55AW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02133&json=true","fetch_graph":"https://pith.science/api/pith-number/JNNX55AWD3K5MQSIBJOUS3T65F/graph.json","fetch_events":"https://pith.science/api/pith-number/JNNX55AWD3K5MQSIBJOUS3T65F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNNX55AWD3K5MQSIBJOUS3T65F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNNX55AWD3K5MQSIBJOUS3T65F/action/storage_attestation","attest_author":"https://pith.science/pith/JNNX55AWD3K5MQSIBJOUS3T65F/action/author_attestation","sign_citation":"https://pith.science/pith/JNNX55AWD3K5MQSIBJOUS3T65F/action/citation_signature","submit_replication":"https://pith.science/pith/JNNX55AWD3K5MQSIBJOUS3T65F/action/replication_record"}},"created_at":"2026-07-05T07:32:25.365221+00:00","updated_at":"2026-07-05T07:32:25.365221+00:00"}