{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TBOE3KUWWGSH3SDB7DIIMTLYCT","short_pith_number":"pith:TBOE3KUW","schema_version":"1.0","canonical_sha256":"985c4daa96b1a47dc861f8d0864d7814e5e88d4e6685c8849e4c93e6bfe7c7e8","source":{"kind":"arxiv","id":"2506.05843","version":1},"attestation_state":"computed","paper":{"title":"FontAdapter: Instant Font Adaptation in Visual Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jaehyun Nam, Jinwoo Shin, Myungkyu Koo, Sangkyung Kwak, Seojin Kim, Subin Kim","submitted_at":"2025-06-06T08:00:49Z","abstract_excerpt":"Text-to-image diffusion models have significantly improved the seamless integration of visual text into diverse image contexts. Recent approaches further improve control over font styles through fine-tuning with predefined font dictionaries. However, adapting unseen fonts outside the preset is computationally expensive, often requiring tens of minutes, making real-time customization impractical. In this paper, we present FontAdapter, a framework that enables visual text generation in unseen fonts within seconds, conditioned on a reference glyph image. To this end, we find that direct training "},"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":"2506.05843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T08:00:49Z","cross_cats_sorted":[],"title_canon_sha256":"6bd92d87316ec97f5cbcd9188908a3eb1c5f6ea95a60756893ea9b6a51026a09","abstract_canon_sha256":"d707367327ac409161b4f847721c40456b0ed9e46c407da82c2d87c819310131"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:11.128997Z","signature_b64":"It4jrNJrmXCN9u+Z7A/f9n9naDtlDaK3lcnqz00FiuIkJnsTUS2bwmr21rxtEVHxn2/RJqEoIqv51W8QaDLwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"985c4daa96b1a47dc861f8d0864d7814e5e88d4e6685c8849e4c93e6bfe7c7e8","last_reissued_at":"2026-07-05T11:17:11.128488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:11.128488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FontAdapter: Instant Font Adaptation in Visual Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jaehyun Nam, Jinwoo Shin, Myungkyu Koo, Sangkyung Kwak, Seojin Kim, Subin Kim","submitted_at":"2025-06-06T08:00:49Z","abstract_excerpt":"Text-to-image diffusion models have significantly improved the seamless integration of visual text into diverse image contexts. Recent approaches further improve control over font styles through fine-tuning with predefined font dictionaries. However, adapting unseen fonts outside the preset is computationally expensive, often requiring tens of minutes, making real-time customization impractical. In this paper, we present FontAdapter, a framework that enables visual text generation in unseen fonts within seconds, conditioned on a reference glyph image. To this end, we find that direct training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05843","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/2506.05843/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":"2506.05843","created_at":"2026-07-05T11:17:11.128545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05843v1","created_at":"2026-07-05T11:17:11.128545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05843","created_at":"2026-07-05T11:17:11.128545+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBOE3KUWWGSH","created_at":"2026-07-05T11:17:11.128545+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBOE3KUWWGSH3SDB","created_at":"2026-07-05T11:17:11.128545+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBOE3KUW","created_at":"2026-07-05T11:17:11.128545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.01593","citing_title":"Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBOE3KUWWGSH3SDB7DIIMTLYCT","json":"https://pith.science/pith/TBOE3KUWWGSH3SDB7DIIMTLYCT.json","graph_json":"https://pith.science/api/pith-number/TBOE3KUWWGSH3SDB7DIIMTLYCT/graph.json","events_json":"https://pith.science/api/pith-number/TBOE3KUWWGSH3SDB7DIIMTLYCT/events.json","paper":"https://pith.science/paper/TBOE3KUW"},"agent_actions":{"view_html":"https://pith.science/pith/TBOE3KUWWGSH3SDB7DIIMTLYCT","download_json":"https://pith.science/pith/TBOE3KUWWGSH3SDB7DIIMTLYCT.json","view_paper":"https://pith.science/paper/TBOE3KUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05843&json=true","fetch_graph":"https://pith.science/api/pith-number/TBOE3KUWWGSH3SDB7DIIMTLYCT/graph.json","fetch_events":"https://pith.science/api/pith-number/TBOE3KUWWGSH3SDB7DIIMTLYCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBOE3KUWWGSH3SDB7DIIMTLYCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBOE3KUWWGSH3SDB7DIIMTLYCT/action/storage_attestation","attest_author":"https://pith.science/pith/TBOE3KUWWGSH3SDB7DIIMTLYCT/action/author_attestation","sign_citation":"https://pith.science/pith/TBOE3KUWWGSH3SDB7DIIMTLYCT/action/citation_signature","submit_replication":"https://pith.science/pith/TBOE3KUWWGSH3SDB7DIIMTLYCT/action/replication_record"}},"created_at":"2026-07-05T11:17:11.128545+00:00","updated_at":"2026-07-05T11:17:11.128545+00:00"}