{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L7DMBNP3EJVQCACD7U5AE3CFZ3","short_pith_number":"pith:L7DMBNP3","schema_version":"1.0","canonical_sha256":"5fc6c0b5fb226b010043fd3a026c45cef59aa8525e83fd2b9e927b7ef1400dc4","source":{"kind":"arxiv","id":"2409.12576","version":1},"attestation_state":"computed","paper":{"title":"StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaxia Li, Jing Li, Nemo Chen, Xu Tang, Zhengguang Zhou","submitted_at":"2024-09-19T08:53:06Z","abstract_excerpt":"Tuning-free personalized image generation methods have achieved significant success in maintaining facial consistency, i.e., identities, even with multiple characters. However, the lack of holistic consistency in scenes with multiple characters hampers these methods' ability to create a cohesive narrative. In this paper, we introduce StoryMaker, a personalization solution that preserves not only facial consistency but also clothing, hairstyles, and body consistency, thus facilitating the creation of a story through a series of images. StoryMaker incorporates conditions based on face identities"},"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":"2409.12576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-19T08:53:06Z","cross_cats_sorted":[],"title_canon_sha256":"3e78c36fb0d253179bd0838308cdff07dbb996ee24fad9cecbfacba9a42add3a","abstract_canon_sha256":"7cac840d93f34464e7ec696a278a1f44a99f25ced87049f437d3f12c7fba7ae7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:09.057776Z","signature_b64":"bCHsfSyvIRt22+KShMSp5p2sJw69/yRKvm8GshL6pNjEUVrXKwiZFbd6aJfMrK7vzEIzeNNH2+ykGAYgBTAlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fc6c0b5fb226b010043fd3a026c45cef59aa8525e83fd2b9e927b7ef1400dc4","last_reissued_at":"2026-07-05T09:09:09.057360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:09.057360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaxia Li, Jing Li, Nemo Chen, Xu Tang, Zhengguang Zhou","submitted_at":"2024-09-19T08:53:06Z","abstract_excerpt":"Tuning-free personalized image generation methods have achieved significant success in maintaining facial consistency, i.e., identities, even with multiple characters. However, the lack of holistic consistency in scenes with multiple characters hampers these methods' ability to create a cohesive narrative. In this paper, we introduce StoryMaker, a personalization solution that preserves not only facial consistency but also clothing, hairstyles, and body consistency, thus facilitating the creation of a story through a series of images. StoryMaker incorporates conditions based on face identities"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12576","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/2409.12576/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":"2409.12576","created_at":"2026-07-05T09:09:09.057418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12576v1","created_at":"2026-07-05T09:09:09.057418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12576","created_at":"2026-07-05T09:09:09.057418+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7DMBNP3EJVQ","created_at":"2026-07-05T09:09:09.057418+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7DMBNP3EJVQCACD","created_at":"2026-07-05T09:09:09.057418+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7DMBNP3","created_at":"2026-07-05T09:09:09.057418+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25079","citing_title":"FreeStory: Training-Free Character Consistency for Free-Form Visual Storytelling","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10620","citing_title":"Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20777","citing_title":"AttriStory: Fine-grained Attribute Realization for Visual Storytelling with Diffusion Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17195","citing_title":"DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7DMBNP3EJVQCACD7U5AE3CFZ3","json":"https://pith.science/pith/L7DMBNP3EJVQCACD7U5AE3CFZ3.json","graph_json":"https://pith.science/api/pith-number/L7DMBNP3EJVQCACD7U5AE3CFZ3/graph.json","events_json":"https://pith.science/api/pith-number/L7DMBNP3EJVQCACD7U5AE3CFZ3/events.json","paper":"https://pith.science/paper/L7DMBNP3"},"agent_actions":{"view_html":"https://pith.science/pith/L7DMBNP3EJVQCACD7U5AE3CFZ3","download_json":"https://pith.science/pith/L7DMBNP3EJVQCACD7U5AE3CFZ3.json","view_paper":"https://pith.science/paper/L7DMBNP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12576&json=true","fetch_graph":"https://pith.science/api/pith-number/L7DMBNP3EJVQCACD7U5AE3CFZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/L7DMBNP3EJVQCACD7U5AE3CFZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7DMBNP3EJVQCACD7U5AE3CFZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7DMBNP3EJVQCACD7U5AE3CFZ3/action/storage_attestation","attest_author":"https://pith.science/pith/L7DMBNP3EJVQCACD7U5AE3CFZ3/action/author_attestation","sign_citation":"https://pith.science/pith/L7DMBNP3EJVQCACD7U5AE3CFZ3/action/citation_signature","submit_replication":"https://pith.science/pith/L7DMBNP3EJVQCACD7U5AE3CFZ3/action/replication_record"}},"created_at":"2026-07-05T09:09:09.057418+00:00","updated_at":"2026-07-05T09:09:09.057418+00:00"}