{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6QBMMMGMN6DALDXZ73AC56QVAC","short_pith_number":"pith:6QBMMMGM","schema_version":"1.0","canonical_sha256":"f402c630cc6f86058ef9fec02efa150095c6f63fd6068fcd4fc2d4708e187037","source":{"kind":"arxiv","id":"2404.02883","version":1},"attestation_state":"computed","paper":{"title":"On the Scalability of Diffusion-based Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ashwin Swaminathan, Hao Li, Orchid Majumder, R. Manmatha, Stefano Ermon, Stefano Soatto, Yang Zou, Ying Wang, Yusheng Xie, Zhuowen Tu","submitted_at":"2024-04-03T17:34:28Z","abstract_excerpt":"Scaling up model and data size has been quite successful for the evolution of LLMs. However, the scaling law for the diffusion based text-to-image (T2I) models is not fully explored. It is also unclear how to efficiently scale the model for better performance at reduced cost. The different training settings and expensive training cost make a fair model comparison extremely difficult. In this work, we empirically study the scaling properties of diffusion based T2I models by performing extensive and rigours ablations on scaling both denoising backbones and training set, including training scaled"},"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":"2404.02883","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-03T17:34:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"67074a4228b575d3a1fc5b564a51e42e266b6b0c75e57caf31d52fce4a27518f","abstract_canon_sha256":"578aaf7ca89852e370fce357a1032b6f16b6951d8f62eb8c9c8e31b39c68e359"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:02.334268Z","signature_b64":"McisGdn82FjHzNgIJgQS6YOQ81tZjY2mqGodNaOPdtBn0xQgOC8nMRCyhM3ZSj8pQAb9f1I1+QFMOGEVQqX7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f402c630cc6f86058ef9fec02efa150095c6f63fd6068fcd4fc2d4708e187037","last_reissued_at":"2026-07-05T08:04:02.333863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:02.333863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Scalability of Diffusion-based Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ashwin Swaminathan, Hao Li, Orchid Majumder, R. Manmatha, Stefano Ermon, Stefano Soatto, Yang Zou, Ying Wang, Yusheng Xie, Zhuowen Tu","submitted_at":"2024-04-03T17:34:28Z","abstract_excerpt":"Scaling up model and data size has been quite successful for the evolution of LLMs. However, the scaling law for the diffusion based text-to-image (T2I) models is not fully explored. It is also unclear how to efficiently scale the model for better performance at reduced cost. The different training settings and expensive training cost make a fair model comparison extremely difficult. In this work, we empirically study the scaling properties of diffusion based T2I models by performing extensive and rigours ablations on scaling both denoising backbones and training set, including training scaled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02883","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/2404.02883/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":"2404.02883","created_at":"2026-07-05T08:04:02.333918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02883v1","created_at":"2026-07-05T08:04:02.333918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02883","created_at":"2026-07-05T08:04:02.333918+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QBMMMGMN6DA","created_at":"2026-07-05T08:04:02.333918+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QBMMMGMN6DALDXZ","created_at":"2026-07-05T08:04:02.333918+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QBMMMGM","created_at":"2026-07-05T08:04:02.333918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07568","citing_title":"A Systematic Study of Behavioral Cloning for Scientific Data Annotation","ref_index":247,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QBMMMGMN6DALDXZ73AC56QVAC","json":"https://pith.science/pith/6QBMMMGMN6DALDXZ73AC56QVAC.json","graph_json":"https://pith.science/api/pith-number/6QBMMMGMN6DALDXZ73AC56QVAC/graph.json","events_json":"https://pith.science/api/pith-number/6QBMMMGMN6DALDXZ73AC56QVAC/events.json","paper":"https://pith.science/paper/6QBMMMGM"},"agent_actions":{"view_html":"https://pith.science/pith/6QBMMMGMN6DALDXZ73AC56QVAC","download_json":"https://pith.science/pith/6QBMMMGMN6DALDXZ73AC56QVAC.json","view_paper":"https://pith.science/paper/6QBMMMGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02883&json=true","fetch_graph":"https://pith.science/api/pith-number/6QBMMMGMN6DALDXZ73AC56QVAC/graph.json","fetch_events":"https://pith.science/api/pith-number/6QBMMMGMN6DALDXZ73AC56QVAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QBMMMGMN6DALDXZ73AC56QVAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QBMMMGMN6DALDXZ73AC56QVAC/action/storage_attestation","attest_author":"https://pith.science/pith/6QBMMMGMN6DALDXZ73AC56QVAC/action/author_attestation","sign_citation":"https://pith.science/pith/6QBMMMGMN6DALDXZ73AC56QVAC/action/citation_signature","submit_replication":"https://pith.science/pith/6QBMMMGMN6DALDXZ73AC56QVAC/action/replication_record"}},"created_at":"2026-07-05T08:04:02.333918+00:00","updated_at":"2026-07-05T08:04:02.333918+00:00"}