{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CQM5SNP2KR3H6XS3FD5ADNW2RP","short_pith_number":"pith:CQM5SNP2","schema_version":"1.0","canonical_sha256":"1419d935fa54767f5e5b28fa01b6da8bcbd14a66370e777679db4b6acb9a46ae","source":{"kind":"arxiv","id":"2405.05945","version":3},"attestation_state":"computed","paper":{"title":"Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Lin, Dongyang Liu, He Tong, Hongsheng Li, Jingwen He, Junlin Xi, Le Zhuo, Longtian Qiu, Peng Gao, Renrui Zhang, Rongjie Huang, Ruoyi Du, Shijie Geng, Tianshuo Yang, Weicai Ye, Wenqi Shao, Xu Luo, Yuhang Zhang, Yu Qiao, Zhengkai Jiang","submitted_at":"2024-05-09T17:35:16Z","abstract_excerpt":"Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this technical report, we introduce the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating lea"},"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":"2405.05945","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T17:35:16Z","cross_cats_sorted":[],"title_canon_sha256":"0eaa036b314fc1911fb26a0adc3dc9a4169df9dc25158eb904b0fd583b0c10df","abstract_canon_sha256":"f44260d539c96cce76217889caa69970d65db154a4ca788f7e6708df8d70304b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:15.234578Z","signature_b64":"j9d9Vm4acZvv6XrimOA7ZgDBz4NFYUlbYVw7rGewTndsOARV/QS/w+VZ9qZRPrgZjZMaipPv3UThwApVNTJiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1419d935fa54767f5e5b28fa01b6da8bcbd14a66370e777679db4b6acb9a46ae","last_reissued_at":"2026-07-05T08:31:15.234066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:15.234066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Lin, Dongyang Liu, He Tong, Hongsheng Li, Jingwen He, Junlin Xi, Le Zhuo, Longtian Qiu, Peng Gao, Renrui Zhang, Rongjie Huang, Ruoyi Du, Shijie Geng, Tianshuo Yang, Weicai Ye, Wenqi Shao, Xu Luo, Yuhang Zhang, Yu Qiao, Zhengkai Jiang","submitted_at":"2024-05-09T17:35:16Z","abstract_excerpt":"Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this technical report, we introduce the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05945","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/2405.05945/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":"2405.05945","created_at":"2026-07-05T08:31:15.234124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.05945v3","created_at":"2026-07-05T08:31:15.234124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05945","created_at":"2026-07-05T08:31:15.234124+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQM5SNP2KR3H","created_at":"2026-07-05T08:31:15.234124+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQM5SNP2KR3H6XS3","created_at":"2026-07-05T08:31:15.234124+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQM5SNP2","created_at":"2026-07-05T08:31:15.234124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04264","citing_title":"UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01399","citing_title":"PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20708","citing_title":"Rethinking Cross-Layer Information Routing in Diffusion Transformers","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30124","citing_title":"SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03603","citing_title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20708","citing_title":"Rethinking Cross-Layer Information Routing in Diffusion Transformers","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21431","citing_title":"iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03233","citing_title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22699","citing_title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04924","citing_title":"Your Pre-trained Diffusion Model Secretly Knows Restoration","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06129","citing_title":"PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP","json":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP.json","graph_json":"https://pith.science/api/pith-number/CQM5SNP2KR3H6XS3FD5ADNW2RP/graph.json","events_json":"https://pith.science/api/pith-number/CQM5SNP2KR3H6XS3FD5ADNW2RP/events.json","paper":"https://pith.science/paper/CQM5SNP2"},"agent_actions":{"view_html":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP","download_json":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP.json","view_paper":"https://pith.science/paper/CQM5SNP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.05945&json=true","fetch_graph":"https://pith.science/api/pith-number/CQM5SNP2KR3H6XS3FD5ADNW2RP/graph.json","fetch_events":"https://pith.science/api/pith-number/CQM5SNP2KR3H6XS3FD5ADNW2RP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/action/storage_attestation","attest_author":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/action/author_attestation","sign_citation":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/action/citation_signature","submit_replication":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/action/replication_record"}},"created_at":"2026-07-05T08:31:15.234124+00:00","updated_at":"2026-07-05T08:31:15.234124+00:00"}