{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2KKXORAFORVS7V56DNPDP7ZJPQ","short_pith_number":"pith:2KKXORAF","schema_version":"1.0","canonical_sha256":"d295774405746b2fd7be1b5e37ff297c2a39fb1a9ae08ee785ed4886cd905ae6","source":{"kind":"arxiv","id":"2410.08531","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Models Need Visual Priors for Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Bai, Luping Zhou, Meng Wei, Shuyang Sun, Wanli Ouyang, Xiaoyu Yue, Zeyu Lu, Zidong Wang","submitted_at":"2024-10-11T05:03:56Z","abstract_excerpt":"Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from the usage of class priors, which only provide coarse and limited conditional information. To address this issue, we propose Diffusion on Diffusion (DoD), an innovative multi-stage generation framework that first extracts visual priors from previously generated samples, then provides rich guidance for the diffusion model leveraging visual priors from the early stages of diffusion sampling. Specifically, we introduce "},"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":"2410.08531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-11T05:03:56Z","cross_cats_sorted":[],"title_canon_sha256":"efec0f3fd4b763a1b3e70c78fac9846d1e338abc4375a42ca427f7c5ad53d7fd","abstract_canon_sha256":"78fc900168543196e12d73ff44078415c9563c42a55377e5360c03b40041b21b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:13.675683Z","signature_b64":"Rf++EDO7//XXrqFC7pt0kycDi9QclKjm5gtrN653eEJmrowvKzDETQtUuw3Ffw1zN5aNqofPxZJ6CjLMZdNXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d295774405746b2fd7be1b5e37ff297c2a39fb1a9ae08ee785ed4886cd905ae6","last_reissued_at":"2026-07-05T09:19:13.675179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:13.675179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Models Need Visual Priors for Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Bai, Luping Zhou, Meng Wei, Shuyang Sun, Wanli Ouyang, Xiaoyu Yue, Zeyu Lu, Zidong Wang","submitted_at":"2024-10-11T05:03:56Z","abstract_excerpt":"Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from the usage of class priors, which only provide coarse and limited conditional information. To address this issue, we propose Diffusion on Diffusion (DoD), an innovative multi-stage generation framework that first extracts visual priors from previously generated samples, then provides rich guidance for the diffusion model leveraging visual priors from the early stages of diffusion sampling. Specifically, we introduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08531","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/2410.08531/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":"2410.08531","created_at":"2026-07-05T09:19:13.675247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08531v1","created_at":"2026-07-05T09:19:13.675247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08531","created_at":"2026-07-05T09:19:13.675247+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KKXORAFORVS","created_at":"2026-07-05T09:19:13.675247+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KKXORAFORVS7V56","created_at":"2026-07-05T09:19:13.675247+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KKXORAF","created_at":"2026-07-05T09:19:13.675247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.20093","citing_title":"StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19365","citing_title":"DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02493","citing_title":"PixelGen: Improving Pixel Diffusion with Perceptual Supervision","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KKXORAFORVS7V56DNPDP7ZJPQ","json":"https://pith.science/pith/2KKXORAFORVS7V56DNPDP7ZJPQ.json","graph_json":"https://pith.science/api/pith-number/2KKXORAFORVS7V56DNPDP7ZJPQ/graph.json","events_json":"https://pith.science/api/pith-number/2KKXORAFORVS7V56DNPDP7ZJPQ/events.json","paper":"https://pith.science/paper/2KKXORAF"},"agent_actions":{"view_html":"https://pith.science/pith/2KKXORAFORVS7V56DNPDP7ZJPQ","download_json":"https://pith.science/pith/2KKXORAFORVS7V56DNPDP7ZJPQ.json","view_paper":"https://pith.science/paper/2KKXORAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08531&json=true","fetch_graph":"https://pith.science/api/pith-number/2KKXORAFORVS7V56DNPDP7ZJPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2KKXORAFORVS7V56DNPDP7ZJPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KKXORAFORVS7V56DNPDP7ZJPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KKXORAFORVS7V56DNPDP7ZJPQ/action/storage_attestation","attest_author":"https://pith.science/pith/2KKXORAFORVS7V56DNPDP7ZJPQ/action/author_attestation","sign_citation":"https://pith.science/pith/2KKXORAFORVS7V56DNPDP7ZJPQ/action/citation_signature","submit_replication":"https://pith.science/pith/2KKXORAFORVS7V56DNPDP7ZJPQ/action/replication_record"}},"created_at":"2026-07-05T09:19:13.675247+00:00","updated_at":"2026-07-05T09:19:13.675247+00:00"}