{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YT2LHGI7AWBEXKVKDGF4VNSQOV","short_pith_number":"pith:YT2LHGI7","schema_version":"1.0","canonical_sha256":"c4f4b3991f05824baaaa198bcab65075494a3a95894a71818319e513cc65e1bd","source":{"kind":"arxiv","id":"2409.19624","version":1},"attestation_state":"computed","paper":{"title":"Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changjie Fan, Chaoyi Zhao, Keqiang Sun, Qinfeng Jin, Wenting Xu, Yuhang Ma, Zeng Zhao, Zhipeng Hu","submitted_at":"2024-09-29T09:15:51Z","abstract_excerpt":"Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consistency, effective foreground-background separation, and diverse pose variation. The core innovation of Storynizor lies in its key modules: ID-Synchronizer and ID-Injector. The ID-Synchronizer employs an auto-mask self-attention module and a mask perceptual loss across inter-frame images to improve the consistency of character generation, vividly repr"},"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":"2409.19624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-29T09:15:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ceca4d6c4ad3e5dc2848436431782ec2e82bdf6c4af129b2761e4c1932b2fecd","abstract_canon_sha256":"e444a0da88fe0ae63ac45d9a20e6df3a83769aa00be14ce5b6cb5c8134457fdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:18.542923Z","signature_b64":"1+mso9G6HKkNovLFw9R9YKAStF8lMC+IaisvvlXtRJw2dBfMMauBajaw/wYqLW3uWn4rQLWHrMXO3e5lk9OoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4f4b3991f05824baaaa198bcab65075494a3a95894a71818319e513cc65e1bd","last_reissued_at":"2026-07-05T09:13:18.542459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:18.542459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changjie Fan, Chaoyi Zhao, Keqiang Sun, Qinfeng Jin, Wenting Xu, Yuhang Ma, Zeng Zhao, Zhipeng Hu","submitted_at":"2024-09-29T09:15:51Z","abstract_excerpt":"Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consistency, effective foreground-background separation, and diverse pose variation. The core innovation of Storynizor lies in its key modules: ID-Synchronizer and ID-Injector. The ID-Synchronizer employs an auto-mask self-attention module and a mask perceptual loss across inter-frame images to improve the consistency of character generation, vividly repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19624","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/2409.19624/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":"2409.19624","created_at":"2026-07-05T09:13:18.542515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19624v1","created_at":"2026-07-05T09:13:18.542515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19624","created_at":"2026-07-05T09:13:18.542515+00:00"},{"alias_kind":"pith_short_12","alias_value":"YT2LHGI7AWBE","created_at":"2026-07-05T09:13:18.542515+00:00"},{"alias_kind":"pith_short_16","alias_value":"YT2LHGI7AWBEXKVK","created_at":"2026-07-05T09:13:18.542515+00:00"},{"alias_kind":"pith_short_8","alias_value":"YT2LHGI7","created_at":"2026-07-05T09:13:18.542515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25079","citing_title":"FreeStory: Training-Free Character Consistency for Free-Form Visual Storytelling","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YT2LHGI7AWBEXKVKDGF4VNSQOV","json":"https://pith.science/pith/YT2LHGI7AWBEXKVKDGF4VNSQOV.json","graph_json":"https://pith.science/api/pith-number/YT2LHGI7AWBEXKVKDGF4VNSQOV/graph.json","events_json":"https://pith.science/api/pith-number/YT2LHGI7AWBEXKVKDGF4VNSQOV/events.json","paper":"https://pith.science/paper/YT2LHGI7"},"agent_actions":{"view_html":"https://pith.science/pith/YT2LHGI7AWBEXKVKDGF4VNSQOV","download_json":"https://pith.science/pith/YT2LHGI7AWBEXKVKDGF4VNSQOV.json","view_paper":"https://pith.science/paper/YT2LHGI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19624&json=true","fetch_graph":"https://pith.science/api/pith-number/YT2LHGI7AWBEXKVKDGF4VNSQOV/graph.json","fetch_events":"https://pith.science/api/pith-number/YT2LHGI7AWBEXKVKDGF4VNSQOV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YT2LHGI7AWBEXKVKDGF4VNSQOV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YT2LHGI7AWBEXKVKDGF4VNSQOV/action/storage_attestation","attest_author":"https://pith.science/pith/YT2LHGI7AWBEXKVKDGF4VNSQOV/action/author_attestation","sign_citation":"https://pith.science/pith/YT2LHGI7AWBEXKVKDGF4VNSQOV/action/citation_signature","submit_replication":"https://pith.science/pith/YT2LHGI7AWBEXKVKDGF4VNSQOV/action/replication_record"}},"created_at":"2026-07-05T09:13:18.542515+00:00","updated_at":"2026-07-05T09:13:18.542515+00:00"}