{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2KIT5NZUKM7UDDKMOMS3HDP4PI","short_pith_number":"pith:2KIT5NZU","schema_version":"1.0","canonical_sha256":"d2913eb734533f418d4c7325b38dfc7a3159f6112cbaedd1ca9b82514dc29c11","source":{"kind":"arxiv","id":"2411.18616","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Self-Distillation for Zero-Shot Customized Image Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Chan, Gordon Wetzstein, Jiajun Wu, Leonidas Guibas, Shengqu Cai, Yunzhi Zhang","submitted_at":"2024-11-27T18:58:52Z","abstract_excerpt":"Text-to-image diffusion models produce impressive results but are frustrating tools for artists who desire fine-grained control. For example, a common use case is to create images of a specific instance in novel contexts, i.e., \"identity-preserving generation\". This setting, along with many other tasks (e.g., relighting), is a natural fit for image+text-conditional generative models. However, there is insufficient high-quality paired data to train such a model directly. We propose Diffusion Self-Distillation, a method for using a pre-trained text-to-image model to generate its own dataset for "},"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":"2411.18616","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:58:52Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"fb309305c4814b2d8766d27bb745714312c0dfcff585f1003969b176605aa9a7","abstract_canon_sha256":"3953283d40a87aaee4523436dcbc2816c5a17a7e133e1d70eb07272f9fbe152a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:24.197494Z","signature_b64":"U2TqY1Ow2SwHYOhjjVXeo9l6j76giq3Ijjdrib403tQ6E1lMK4Lmk60EPusaQ8DIA6ti7ze4hkbB6OkYtlwxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2913eb734533f418d4c7325b38dfc7a3159f6112cbaedd1ca9b82514dc29c11","last_reissued_at":"2026-07-05T09:41:24.196965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:24.196965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Self-Distillation for Zero-Shot Customized Image Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Eric Chan, Gordon Wetzstein, Jiajun Wu, Leonidas Guibas, Shengqu Cai, Yunzhi Zhang","submitted_at":"2024-11-27T18:58:52Z","abstract_excerpt":"Text-to-image diffusion models produce impressive results but are frustrating tools for artists who desire fine-grained control. For example, a common use case is to create images of a specific instance in novel contexts, i.e., \"identity-preserving generation\". This setting, along with many other tasks (e.g., relighting), is a natural fit for image+text-conditional generative models. However, there is insufficient high-quality paired data to train such a model directly. We propose Diffusion Self-Distillation, a method for using a pre-trained text-to-image model to generate its own dataset for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18616","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/2411.18616/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":"2411.18616","created_at":"2026-07-05T09:41:24.197026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18616v1","created_at":"2026-07-05T09:41:24.197026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18616","created_at":"2026-07-05T09:41:24.197026+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KIT5NZUKM7U","created_at":"2026-07-05T09:41:24.197026+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KIT5NZUKM7UDDKM","created_at":"2026-07-05T09:41:24.197026+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KIT5NZU","created_at":"2026-07-05T09:41:24.197026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KIT5NZUKM7UDDKMOMS3HDP4PI","json":"https://pith.science/pith/2KIT5NZUKM7UDDKMOMS3HDP4PI.json","graph_json":"https://pith.science/api/pith-number/2KIT5NZUKM7UDDKMOMS3HDP4PI/graph.json","events_json":"https://pith.science/api/pith-number/2KIT5NZUKM7UDDKMOMS3HDP4PI/events.json","paper":"https://pith.science/paper/2KIT5NZU"},"agent_actions":{"view_html":"https://pith.science/pith/2KIT5NZUKM7UDDKMOMS3HDP4PI","download_json":"https://pith.science/pith/2KIT5NZUKM7UDDKMOMS3HDP4PI.json","view_paper":"https://pith.science/paper/2KIT5NZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18616&json=true","fetch_graph":"https://pith.science/api/pith-number/2KIT5NZUKM7UDDKMOMS3HDP4PI/graph.json","fetch_events":"https://pith.science/api/pith-number/2KIT5NZUKM7UDDKMOMS3HDP4PI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KIT5NZUKM7UDDKMOMS3HDP4PI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KIT5NZUKM7UDDKMOMS3HDP4PI/action/storage_attestation","attest_author":"https://pith.science/pith/2KIT5NZUKM7UDDKMOMS3HDP4PI/action/author_attestation","sign_citation":"https://pith.science/pith/2KIT5NZUKM7UDDKMOMS3HDP4PI/action/citation_signature","submit_replication":"https://pith.science/pith/2KIT5NZUKM7UDDKMOMS3HDP4PI/action/replication_record"}},"created_at":"2026-07-05T09:41:24.197026+00:00","updated_at":"2026-07-05T09:41:24.197026+00:00"}