{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PNJX6PJMJ7SDMRR2FTL7DY4KCD","short_pith_number":"pith:PNJX6PJM","schema_version":"1.0","canonical_sha256":"7b537f3d2c4fe436463a2cd7f1e38a10c4853c5134a322ff83bda7383d5e0758","source":{"kind":"arxiv","id":"2508.03735","version":1},"attestation_state":"computed","paper":{"title":"StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gopalji Gaur, Mohammadreza Zolfaghari, Thomas Brox","submitted_at":"2025-07-31T11:24:40Z","abstract_excerpt":"Generating a coherent sequence of images that tells a visual story, using text-to-image diffusion models, often faces the critical challenge of maintaining subject consistency across all story scenes. Existing approaches, which typically rely on fine-tuning or retraining models, are computationally expensive, time-consuming, and often interfere with the model's pre-existing capabilities. In this paper, we follow a training-free approach and propose an efficient consistent-subject-generation method. This approach works seamlessly with pre-trained diffusion models by introducing masked cross-ima"},"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":"2508.03735","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T11:24:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b4efebb81866a145fb4aa9df6260b50e6734f83a58e9b496c7549b44953e383","abstract_canon_sha256":"f25b7a3b71a90e44bd409fe881c0749267eef6857d674c8a78d7c6769ed1703d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:14.089434Z","signature_b64":"L5q3a6z+41++iGcknaske8PsbhEgCM22pXMzqWFyNkCkCrCuWf4qDCzKB3FbP/PC1I3TSfdZJjE/NWsIh/qfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b537f3d2c4fe436463a2cd7f1e38a10c4853c5134a322ff83bda7383d5e0758","last_reissued_at":"2026-07-05T11:49:14.088845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:14.088845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gopalji Gaur, Mohammadreza Zolfaghari, Thomas Brox","submitted_at":"2025-07-31T11:24:40Z","abstract_excerpt":"Generating a coherent sequence of images that tells a visual story, using text-to-image diffusion models, often faces the critical challenge of maintaining subject consistency across all story scenes. Existing approaches, which typically rely on fine-tuning or retraining models, are computationally expensive, time-consuming, and often interfere with the model's pre-existing capabilities. In this paper, we follow a training-free approach and propose an efficient consistent-subject-generation method. This approach works seamlessly with pre-trained diffusion models by introducing masked cross-ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03735","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/2508.03735/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":"2508.03735","created_at":"2026-07-05T11:49:14.088913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03735v1","created_at":"2026-07-05T11:49:14.088913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03735","created_at":"2026-07-05T11:49:14.088913+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNJX6PJMJ7SD","created_at":"2026-07-05T11:49:14.088913+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNJX6PJMJ7SDMRR2","created_at":"2026-07-05T11:49:14.088913+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNJX6PJM","created_at":"2026-07-05T11:49:14.088913+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/PNJX6PJMJ7SDMRR2FTL7DY4KCD","json":"https://pith.science/pith/PNJX6PJMJ7SDMRR2FTL7DY4KCD.json","graph_json":"https://pith.science/api/pith-number/PNJX6PJMJ7SDMRR2FTL7DY4KCD/graph.json","events_json":"https://pith.science/api/pith-number/PNJX6PJMJ7SDMRR2FTL7DY4KCD/events.json","paper":"https://pith.science/paper/PNJX6PJM"},"agent_actions":{"view_html":"https://pith.science/pith/PNJX6PJMJ7SDMRR2FTL7DY4KCD","download_json":"https://pith.science/pith/PNJX6PJMJ7SDMRR2FTL7DY4KCD.json","view_paper":"https://pith.science/paper/PNJX6PJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03735&json=true","fetch_graph":"https://pith.science/api/pith-number/PNJX6PJMJ7SDMRR2FTL7DY4KCD/graph.json","fetch_events":"https://pith.science/api/pith-number/PNJX6PJMJ7SDMRR2FTL7DY4KCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNJX6PJMJ7SDMRR2FTL7DY4KCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNJX6PJMJ7SDMRR2FTL7DY4KCD/action/storage_attestation","attest_author":"https://pith.science/pith/PNJX6PJMJ7SDMRR2FTL7DY4KCD/action/author_attestation","sign_citation":"https://pith.science/pith/PNJX6PJMJ7SDMRR2FTL7DY4KCD/action/citation_signature","submit_replication":"https://pith.science/pith/PNJX6PJMJ7SDMRR2FTL7DY4KCD/action/replication_record"}},"created_at":"2026-07-05T11:49:14.088913+00:00","updated_at":"2026-07-05T11:49:14.088913+00:00"}