{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ICNVYHLEOWWWZ3ZDTWH2BMNOUT","short_pith_number":"pith:ICNVYHLE","schema_version":"1.0","canonical_sha256":"409b5c1d6475ad6cef239d8fa0b1aea4e91f11280a90402d08953582368007ee","source":{"kind":"arxiv","id":"2411.15245","version":1},"attestation_state":"computed","paper":{"title":"AnyText2: Visual Text Generation and Editing With Customizable Attributes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liefeng Bo, Yifeng Geng, Yuxiang Tuo","submitted_at":"2024-11-22T03:31:56Z","abstract_excerpt":"As the text-to-image (T2I) domain progresses, generating text that seamlessly integrates with visual content has garnered significant attention. However, even with accurate text generation, the inability to control font and color can greatly limit certain applications, and this issue remains insufficiently addressed. This paper introduces AnyText2, a novel method that enables precise control over multilingual text attributes in natural scene image generation and editing. Our approach consists of two main components. First, we propose a WriteNet+AttnX architecture that injects text rendering ca"},"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":"2411.15245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T03:31:56Z","cross_cats_sorted":[],"title_canon_sha256":"f7125908188344e8db265ee29397a45c72641d449fcd8295bb3fd64c0fccfefa","abstract_canon_sha256":"e95e36e10d7369a9e457ec6a3ed098db39da5b95df582860b5ccbd0bc3cfd591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:31.810867Z","signature_b64":"t9YgnVOchXSmZUJJ1VlcjvdzYs/Iw3bnuK8OAJ7aPX4aZQKT3HlnIf5NrNUlkudHESoNSbxza+jys0IaFcreCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"409b5c1d6475ad6cef239d8fa0b1aea4e91f11280a90402d08953582368007ee","last_reissued_at":"2026-07-05T09:39:31.810433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:31.810433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnyText2: Visual Text Generation and Editing With Customizable Attributes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liefeng Bo, Yifeng Geng, Yuxiang Tuo","submitted_at":"2024-11-22T03:31:56Z","abstract_excerpt":"As the text-to-image (T2I) domain progresses, generating text that seamlessly integrates with visual content has garnered significant attention. However, even with accurate text generation, the inability to control font and color can greatly limit certain applications, and this issue remains insufficiently addressed. This paper introduces AnyText2, a novel method that enables precise control over multilingual text attributes in natural scene image generation and editing. Our approach consists of two main components. First, we propose a WriteNet+AttnX architecture that injects text rendering ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15245","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/2411.15245/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":"2411.15245","created_at":"2026-07-05T09:39:31.810483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15245v1","created_at":"2026-07-05T09:39:31.810483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15245","created_at":"2026-07-05T09:39:31.810483+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICNVYHLEOWWW","created_at":"2026-07-05T09:39:31.810483+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICNVYHLEOWWWZ3ZD","created_at":"2026-07-05T09:39:31.810483+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICNVYHLE","created_at":"2026-07-05T09:39:31.810483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23254","citing_title":"SteerVTE: Seamless Video Text Editing with Style and Glyph Control","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05730","citing_title":"TextWand: A Unified Framework for Scene Text Editing","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04479","citing_title":"Evaluating Reasoning Fidelity in Visual Text Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15523","citing_title":"Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15523","citing_title":"Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13285","citing_title":"SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Design","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24171","citing_title":"POCA: Pareto-Optimal Curriculum Alignment for Visual Text Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19858","citing_title":"Wan-Image: Pushing the Boundaries of Generative Visual Intelligence","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ICNVYHLEOWWWZ3ZDTWH2BMNOUT","json":"https://pith.science/pith/ICNVYHLEOWWWZ3ZDTWH2BMNOUT.json","graph_json":"https://pith.science/api/pith-number/ICNVYHLEOWWWZ3ZDTWH2BMNOUT/graph.json","events_json":"https://pith.science/api/pith-number/ICNVYHLEOWWWZ3ZDTWH2BMNOUT/events.json","paper":"https://pith.science/paper/ICNVYHLE"},"agent_actions":{"view_html":"https://pith.science/pith/ICNVYHLEOWWWZ3ZDTWH2BMNOUT","download_json":"https://pith.science/pith/ICNVYHLEOWWWZ3ZDTWH2BMNOUT.json","view_paper":"https://pith.science/paper/ICNVYHLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15245&json=true","fetch_graph":"https://pith.science/api/pith-number/ICNVYHLEOWWWZ3ZDTWH2BMNOUT/graph.json","fetch_events":"https://pith.science/api/pith-number/ICNVYHLEOWWWZ3ZDTWH2BMNOUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICNVYHLEOWWWZ3ZDTWH2BMNOUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICNVYHLEOWWWZ3ZDTWH2BMNOUT/action/storage_attestation","attest_author":"https://pith.science/pith/ICNVYHLEOWWWZ3ZDTWH2BMNOUT/action/author_attestation","sign_citation":"https://pith.science/pith/ICNVYHLEOWWWZ3ZDTWH2BMNOUT/action/citation_signature","submit_replication":"https://pith.science/pith/ICNVYHLEOWWWZ3ZDTWH2BMNOUT/action/replication_record"}},"created_at":"2026-07-05T09:39:31.810483+00:00","updated_at":"2026-07-05T09:39:31.810483+00:00"}