{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RESUPT5M7SBD7D2HKPSKEVMNBN","short_pith_number":"pith:RESUPT5M","schema_version":"1.0","canonical_sha256":"892547cfacfc823f8f4753e4a2558d0b66d9d24a53de0cf06c075e17a9bf5588","source":{"kind":"arxiv","id":"2407.12718","version":2},"attestation_state":"computed","paper":{"title":"SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Liu, Xingchao Liu, Yuanzhi Zhu","submitted_at":"2024-07-17T16:38:45Z","abstract_excerpt":"Diffusion models excel in high-quality generation but suffer from slow inference due to iterative sampling. While recent methods have successfully transformed diffusion models into one-step generators, they neglect model size reduction, limiting their applicability in compute-constrained scenarios. This paper aims to develop small, efficient one-step diffusion models based on the powerful rectified flow framework, by exploring joint compression of inference steps and model size. The rectified flow framework trains one-step generative models using two operations, reflow and distillation. Compar"},"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":"2407.12718","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:38:45Z","cross_cats_sorted":[],"title_canon_sha256":"38c56ae0fef8c63b3d281377ebd9899b8ef7ef3f36069f05ed653d3f84470dd8","abstract_canon_sha256":"b31af7b116d0c68e3340c6b55eac05ad5871105cc36dd8c763e5d16ad57e84bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:31.563248Z","signature_b64":"9kQLBsC9ODDNRKVCJgIBDKKRj8GjTlynPcS/76c2LLPuSDW+TrJeuqk29sdyDRjOomhEHRd5R6NwSsxeCd6lCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"892547cfacfc823f8f4753e4a2558d0b66d9d24a53de0cf06c075e17a9bf5588","last_reissued_at":"2026-07-05T08:45:31.562860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:31.562860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Liu, Xingchao Liu, Yuanzhi Zhu","submitted_at":"2024-07-17T16:38:45Z","abstract_excerpt":"Diffusion models excel in high-quality generation but suffer from slow inference due to iterative sampling. While recent methods have successfully transformed diffusion models into one-step generators, they neglect model size reduction, limiting their applicability in compute-constrained scenarios. This paper aims to develop small, efficient one-step diffusion models based on the powerful rectified flow framework, by exploring joint compression of inference steps and model size. The rectified flow framework trains one-step generative models using two operations, reflow and distillation. Compar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12718","kind":"arxiv","version":2},"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/2407.12718/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":"2407.12718","created_at":"2026-07-05T08:45:31.562917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12718v2","created_at":"2026-07-05T08:45:31.562917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12718","created_at":"2026-07-05T08:45:31.562917+00:00"},{"alias_kind":"pith_short_12","alias_value":"RESUPT5M7SBD","created_at":"2026-07-05T08:45:31.562917+00:00"},{"alias_kind":"pith_short_16","alias_value":"RESUPT5M7SBD7D2H","created_at":"2026-07-05T08:45:31.562917+00:00"},{"alias_kind":"pith_short_8","alias_value":"RESUPT5M","created_at":"2026-07-05T08:45:31.562917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06805","citing_title":"Efficient Diffusion Models: A Survey","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RESUPT5M7SBD7D2HKPSKEVMNBN","json":"https://pith.science/pith/RESUPT5M7SBD7D2HKPSKEVMNBN.json","graph_json":"https://pith.science/api/pith-number/RESUPT5M7SBD7D2HKPSKEVMNBN/graph.json","events_json":"https://pith.science/api/pith-number/RESUPT5M7SBD7D2HKPSKEVMNBN/events.json","paper":"https://pith.science/paper/RESUPT5M"},"agent_actions":{"view_html":"https://pith.science/pith/RESUPT5M7SBD7D2HKPSKEVMNBN","download_json":"https://pith.science/pith/RESUPT5M7SBD7D2HKPSKEVMNBN.json","view_paper":"https://pith.science/paper/RESUPT5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12718&json=true","fetch_graph":"https://pith.science/api/pith-number/RESUPT5M7SBD7D2HKPSKEVMNBN/graph.json","fetch_events":"https://pith.science/api/pith-number/RESUPT5M7SBD7D2HKPSKEVMNBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RESUPT5M7SBD7D2HKPSKEVMNBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RESUPT5M7SBD7D2HKPSKEVMNBN/action/storage_attestation","attest_author":"https://pith.science/pith/RESUPT5M7SBD7D2HKPSKEVMNBN/action/author_attestation","sign_citation":"https://pith.science/pith/RESUPT5M7SBD7D2HKPSKEVMNBN/action/citation_signature","submit_replication":"https://pith.science/pith/RESUPT5M7SBD7D2HKPSKEVMNBN/action/replication_record"}},"created_at":"2026-07-05T08:45:31.562917+00:00","updated_at":"2026-07-05T08:45:31.562917+00:00"}