{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5N2AMIE7PJ3BNEAFWB752TLJLU","short_pith_number":"pith:5N2AMIE7","schema_version":"1.0","canonical_sha256":"eb7406209f7a76169005b07fdd4d695d2e98d1e6bfed0230fcb602b7e9692876","source":{"kind":"arxiv","id":"2412.00136","version":3},"attestation_state":"computed","paper":{"title":"FonTS: Text Rendering with Typography and Style Controls","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dengming Zhang, Jiaming Liu, Wenda Shi, Xingxing Zou, Yiren Song","submitted_at":"2024-11-28T16:19:37Z","abstract_excerpt":"Visual text rendering are widespread in various real-world applications, requiring careful font selection and typographic choices. Recent progress in diffusion transformer (DiT)-based text-to-image (T2I) models show promise in automating these processes. However, these methods still encounter challenges like inconsistent fonts, style variation, and limited fine-grained control, particularly at the word-level. This paper proposes a two-stage DiT-based pipeline to address these problems by enhancing controllability over typography and style in text rendering. We introduce typography control fine"},"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":"2412.00136","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T16:19:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9de7aedf2b74e9bfab98131602469ac723c12cd969c4762fba6d0ac12c84664f","abstract_canon_sha256":"3c8b7531acaf451416a7708f6002ea8a4552e18939e22aaedee5764559a1ad4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:30.958080Z","signature_b64":"ObL2NI3xFAkORPSVtsr08OOzd7vVv8cH+HBz6tzLeV7+FkAbpS3eCSr4I2u1fsyJJlxaetgEJ/FoO8B6P2+BAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb7406209f7a76169005b07fdd4d695d2e98d1e6bfed0230fcb602b7e9692876","last_reissued_at":"2026-07-05T11:35:30.957615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:30.957615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FonTS: Text Rendering with Typography and Style Controls","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dengming Zhang, Jiaming Liu, Wenda Shi, Xingxing Zou, Yiren Song","submitted_at":"2024-11-28T16:19:37Z","abstract_excerpt":"Visual text rendering are widespread in various real-world applications, requiring careful font selection and typographic choices. Recent progress in diffusion transformer (DiT)-based text-to-image (T2I) models show promise in automating these processes. However, these methods still encounter challenges like inconsistent fonts, style variation, and limited fine-grained control, particularly at the word-level. This paper proposes a two-stage DiT-based pipeline to address these problems by enhancing controllability over typography and style in text rendering. We introduce typography control fine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00136","kind":"arxiv","version":3},"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/2412.00136/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":"2412.00136","created_at":"2026-07-05T11:35:30.957673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00136v3","created_at":"2026-07-05T11:35:30.957673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00136","created_at":"2026-07-05T11:35:30.957673+00:00"},{"alias_kind":"pith_short_12","alias_value":"5N2AMIE7PJ3B","created_at":"2026-07-05T11:35:30.957673+00:00"},{"alias_kind":"pith_short_16","alias_value":"5N2AMIE7PJ3BNEAF","created_at":"2026-07-05T11:35:30.957673+00:00"},{"alias_kind":"pith_short_8","alias_value":"5N2AMIE7","created_at":"2026-07-05T11:35:30.957673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12280","citing_title":"Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06066","citing_title":"FontFusion: Enhancing Generative Text in Diffusion Models with Typographic Conditioning","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5N2AMIE7PJ3BNEAFWB752TLJLU","json":"https://pith.science/pith/5N2AMIE7PJ3BNEAFWB752TLJLU.json","graph_json":"https://pith.science/api/pith-number/5N2AMIE7PJ3BNEAFWB752TLJLU/graph.json","events_json":"https://pith.science/api/pith-number/5N2AMIE7PJ3BNEAFWB752TLJLU/events.json","paper":"https://pith.science/paper/5N2AMIE7"},"agent_actions":{"view_html":"https://pith.science/pith/5N2AMIE7PJ3BNEAFWB752TLJLU","download_json":"https://pith.science/pith/5N2AMIE7PJ3BNEAFWB752TLJLU.json","view_paper":"https://pith.science/paper/5N2AMIE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00136&json=true","fetch_graph":"https://pith.science/api/pith-number/5N2AMIE7PJ3BNEAFWB752TLJLU/graph.json","fetch_events":"https://pith.science/api/pith-number/5N2AMIE7PJ3BNEAFWB752TLJLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5N2AMIE7PJ3BNEAFWB752TLJLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5N2AMIE7PJ3BNEAFWB752TLJLU/action/storage_attestation","attest_author":"https://pith.science/pith/5N2AMIE7PJ3BNEAFWB752TLJLU/action/author_attestation","sign_citation":"https://pith.science/pith/5N2AMIE7PJ3BNEAFWB752TLJLU/action/citation_signature","submit_replication":"https://pith.science/pith/5N2AMIE7PJ3BNEAFWB752TLJLU/action/replication_record"}},"created_at":"2026-07-05T11:35:30.957673+00:00","updated_at":"2026-07-05T11:35:30.957673+00:00"}