{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M7KTXSDDGTPTX34DMN53DMX46O","short_pith_number":"pith:M7KTXSDD","schema_version":"1.0","canonical_sha256":"67d53bc86334df3bef83637bb1b2fcf3a7b388bacf3cf08d3a4e6d797b790b1b","source":{"kind":"arxiv","id":"2406.04324","version":2},"attestation_state":"computed","paper":{"title":"SF-V: Single Forward Video Generation Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Anil Kag, Dimitris Metaxas, Ivan Skorokhodov, Jian Ren, Junli Cao, Sergey Tulyakov, Willi Menapace, Yanwu Xu, Yanyu Li, Yushu Wu, Zhixing Zhang","submitted_at":"2024-06-06T17:58:27Z","abstract_excerpt":"Diffusion-based video generation models have demonstrated remarkable success in obtaining high-fidelity videos through the iterative denoising process. However, these models require multiple denoising steps during sampling, resulting in high computational costs. In this work, we propose a novel approach to obtain single-step video generation models by leveraging adversarial training to fine-tune pre-trained video diffusion models. We show that, through the adversarial training, the multi-steps video diffusion model, i.e., Stable Video Diffusion (SVD), can be trained to perform single forward p"},"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":"2406.04324","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:58:27Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"29d561eb032f950434681fc46183d6256d13e9cbdc4293180fa6d277c15182c1","abstract_canon_sha256":"21ad1163d754167e56a980ec5e0da97ff5b551288923e60b283fe1a686910d9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:44.081003Z","signature_b64":"7CMIm4agLnggZuXqLo7F2J736mXRQBLigGtPzTQiwhsN7Ea7PAjtDXSuDzERcVsO1yjXE4SgIWvEFsJUXpPLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67d53bc86334df3bef83637bb1b2fcf3a7b388bacf3cf08d3a4e6d797b790b1b","last_reissued_at":"2026-07-05T09:25:44.080451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:44.080451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SF-V: Single Forward Video Generation Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Anil Kag, Dimitris Metaxas, Ivan Skorokhodov, Jian Ren, Junli Cao, Sergey Tulyakov, Willi Menapace, Yanwu Xu, Yanyu Li, Yushu Wu, Zhixing Zhang","submitted_at":"2024-06-06T17:58:27Z","abstract_excerpt":"Diffusion-based video generation models have demonstrated remarkable success in obtaining high-fidelity videos through the iterative denoising process. However, these models require multiple denoising steps during sampling, resulting in high computational costs. In this work, we propose a novel approach to obtain single-step video generation models by leveraging adversarial training to fine-tune pre-trained video diffusion models. We show that, through the adversarial training, the multi-steps video diffusion model, i.e., Stable Video Diffusion (SVD), can be trained to perform single forward p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04324","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/2406.04324/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":"2406.04324","created_at":"2026-07-05T09:25:44.080527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04324v2","created_at":"2026-07-05T09:25:44.080527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04324","created_at":"2026-07-05T09:25:44.080527+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7KTXSDDGTPT","created_at":"2026-07-05T09:25:44.080527+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7KTXSDDGTPTX34D","created_at":"2026-07-05T09:25:44.080527+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7KTXSDD","created_at":"2026-07-05T09:25:44.080527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.15689","citing_title":"DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7KTXSDDGTPTX34DMN53DMX46O","json":"https://pith.science/pith/M7KTXSDDGTPTX34DMN53DMX46O.json","graph_json":"https://pith.science/api/pith-number/M7KTXSDDGTPTX34DMN53DMX46O/graph.json","events_json":"https://pith.science/api/pith-number/M7KTXSDDGTPTX34DMN53DMX46O/events.json","paper":"https://pith.science/paper/M7KTXSDD"},"agent_actions":{"view_html":"https://pith.science/pith/M7KTXSDDGTPTX34DMN53DMX46O","download_json":"https://pith.science/pith/M7KTXSDDGTPTX34DMN53DMX46O.json","view_paper":"https://pith.science/paper/M7KTXSDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04324&json=true","fetch_graph":"https://pith.science/api/pith-number/M7KTXSDDGTPTX34DMN53DMX46O/graph.json","fetch_events":"https://pith.science/api/pith-number/M7KTXSDDGTPTX34DMN53DMX46O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7KTXSDDGTPTX34DMN53DMX46O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7KTXSDDGTPTX34DMN53DMX46O/action/storage_attestation","attest_author":"https://pith.science/pith/M7KTXSDDGTPTX34DMN53DMX46O/action/author_attestation","sign_citation":"https://pith.science/pith/M7KTXSDDGTPTX34DMN53DMX46O/action/citation_signature","submit_replication":"https://pith.science/pith/M7KTXSDDGTPTX34DMN53DMX46O/action/replication_record"}},"created_at":"2026-07-05T09:25:44.080527+00:00","updated_at":"2026-07-05T09:25:44.080527+00:00"}