{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EHR722DPBUBSK4QLABXT2GFNY5","short_pith_number":"pith:EHR722DP","schema_version":"1.0","canonical_sha256":"21e3fd686f0d0325720b006f3d18adc75e18c5e655566297606ae1343a3f0f67","source":{"kind":"arxiv","id":"2401.14688","version":3},"attestation_state":"computed","paper":{"title":"Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dixiang Zhang, Jiaxing Zhang, Junyu Lu, Pingjian Zhang, Renliang Sun, Ruyi Gan, Xiaojun Wu, Yan Song, Ziwei Wu","submitted_at":"2024-01-26T07:17:50Z","abstract_excerpt":"Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support. To address this need, we present Taiyi-Diffusion-XL, a new Chinese and English bilingual text-to-image model which is developed by extending the capabilities of CLIP and Stable-Diffusion-XL through a process of bilingual continuous pre-training. This approach includes the efficient expansion of vocabulary by integrating the most frequently used Chinese characters into CLIP's tokenizer and embedding laye"},"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":"2401.14688","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T07:17:50Z","cross_cats_sorted":[],"title_canon_sha256":"32953adb8c75fa6eca5249e9b4379ee0ff519e416920e358ba7cf8d96f0dead2","abstract_canon_sha256":"0eb3b10538178f26d0c6be8b0e2bc83c1980bdc3bc1aae97243ef4bdb200be7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:34.760100Z","signature_b64":"SlkJ5xaMn+mh2u3lIe8l5NOrqH3eP0Wmm+WiCtVyLdtrXtQ/u3ERT0tpo7BjlhZJORMIhMaBO+3bqF/MdKsxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21e3fd686f0d0325720b006f3d18adc75e18c5e655566297606ae1343a3f0f67","last_reissued_at":"2026-07-05T08:33:34.759622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:34.759622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dixiang Zhang, Jiaxing Zhang, Junyu Lu, Pingjian Zhang, Renliang Sun, Ruyi Gan, Xiaojun Wu, Yan Song, Ziwei Wu","submitted_at":"2024-01-26T07:17:50Z","abstract_excerpt":"Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support. To address this need, we present Taiyi-Diffusion-XL, a new Chinese and English bilingual text-to-image model which is developed by extending the capabilities of CLIP and Stable-Diffusion-XL through a process of bilingual continuous pre-training. This approach includes the efficient expansion of vocabulary by integrating the most frequently used Chinese characters into CLIP's tokenizer and embedding laye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14688","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/2401.14688/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":"2401.14688","created_at":"2026-07-05T08:33:34.759680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14688v3","created_at":"2026-07-05T08:33:34.759680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14688","created_at":"2026-07-05T08:33:34.759680+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHR722DPBUBS","created_at":"2026-07-05T08:33:34.759680+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHR722DPBUBSK4QL","created_at":"2026-07-05T08:33:34.759680+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHR722DP","created_at":"2026-07-05T08:33:34.759680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28421","citing_title":"JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2405.08748","citing_title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHR722DPBUBSK4QLABXT2GFNY5","json":"https://pith.science/pith/EHR722DPBUBSK4QLABXT2GFNY5.json","graph_json":"https://pith.science/api/pith-number/EHR722DPBUBSK4QLABXT2GFNY5/graph.json","events_json":"https://pith.science/api/pith-number/EHR722DPBUBSK4QLABXT2GFNY5/events.json","paper":"https://pith.science/paper/EHR722DP"},"agent_actions":{"view_html":"https://pith.science/pith/EHR722DPBUBSK4QLABXT2GFNY5","download_json":"https://pith.science/pith/EHR722DPBUBSK4QLABXT2GFNY5.json","view_paper":"https://pith.science/paper/EHR722DP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14688&json=true","fetch_graph":"https://pith.science/api/pith-number/EHR722DPBUBSK4QLABXT2GFNY5/graph.json","fetch_events":"https://pith.science/api/pith-number/EHR722DPBUBSK4QLABXT2GFNY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHR722DPBUBSK4QLABXT2GFNY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHR722DPBUBSK4QLABXT2GFNY5/action/storage_attestation","attest_author":"https://pith.science/pith/EHR722DPBUBSK4QLABXT2GFNY5/action/author_attestation","sign_citation":"https://pith.science/pith/EHR722DPBUBSK4QLABXT2GFNY5/action/citation_signature","submit_replication":"https://pith.science/pith/EHR722DPBUBSK4QLABXT2GFNY5/action/replication_record"}},"created_at":"2026-07-05T08:33:34.759680+00:00","updated_at":"2026-07-05T08:33:34.759680+00:00"}