{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SNSR26KB2TAKQYDMDQXS4IWLMK","short_pith_number":"pith:SNSR26KB","schema_version":"1.0","canonical_sha256":"93651d7941d4c0a8606c1c2f2e22cb629f90240e69f5713c9d3a367f6171b8ad","source":{"kind":"arxiv","id":"2304.06025","version":4},"attestation_state":"computed","paper":{"title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Ira Kemelmacher-Shlizerman, Johanna Karras, Ting-Chun Wang","submitted_at":"2023-04-12T17:59:17Z","abstract_excerpt":"We present DreamPose, a diffusion-based method for generating animated fashion videos from still images. Given an image and a sequence of human body poses, our method synthesizes a video containing both human and fabric motion. To achieve this, we transform a pretrained text-to-image model (Stable Diffusion) into a pose-and-image guided video synthesis model, using a novel fine-tuning strategy, a set of architectural changes to support the added conditioning signals, and techniques to encourage temporal consistency. We fine-tune on a collection of fashion videos from the UBC Fashion dataset. W"},"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":"2304.06025","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T17:59:17Z","cross_cats_sorted":[],"title_canon_sha256":"af11fe974caf584ab4f676ea86c231fff7813455b39d1da56fa94210080904ae","abstract_canon_sha256":"5af3653538a4b1c2d0af984605e592ee3097d1489edc2675b3f4f18fccac04a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:08.824299Z","signature_b64":"w9Bazuir87/ZikJTxvFxleYK0AnaEVtDGY2rG0u1KE1wvGQ8S5U59wYIzs8OCNU/6iM+9ophTHEeEgG8D6ckBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93651d7941d4c0a8606c1c2f2e22cb629f90240e69f5713c9d3a367f6171b8ad","last_reissued_at":"2026-07-05T07:07:08.823797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:08.823797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Ira Kemelmacher-Shlizerman, Johanna Karras, Ting-Chun Wang","submitted_at":"2023-04-12T17:59:17Z","abstract_excerpt":"We present DreamPose, a diffusion-based method for generating animated fashion videos from still images. Given an image and a sequence of human body poses, our method synthesizes a video containing both human and fabric motion. To achieve this, we transform a pretrained text-to-image model (Stable Diffusion) into a pose-and-image guided video synthesis model, using a novel fine-tuning strategy, a set of architectural changes to support the added conditioning signals, and techniques to encourage temporal consistency. We fine-tune on a collection of fashion videos from the UBC Fashion dataset. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06025","kind":"arxiv","version":4},"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/2304.06025/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":"2304.06025","created_at":"2026-07-05T07:07:08.823854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06025v4","created_at":"2026-07-05T07:07:08.823854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06025","created_at":"2026-07-05T07:07:08.823854+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNSR26KB2TAK","created_at":"2026-07-05T07:07:08.823854+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNSR26KB2TAKQYDM","created_at":"2026-07-05T07:07:08.823854+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNSR26KB","created_at":"2026-07-05T07:07:08.823854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2404.02101","citing_title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNSR26KB2TAKQYDMDQXS4IWLMK","json":"https://pith.science/pith/SNSR26KB2TAKQYDMDQXS4IWLMK.json","graph_json":"https://pith.science/api/pith-number/SNSR26KB2TAKQYDMDQXS4IWLMK/graph.json","events_json":"https://pith.science/api/pith-number/SNSR26KB2TAKQYDMDQXS4IWLMK/events.json","paper":"https://pith.science/paper/SNSR26KB"},"agent_actions":{"view_html":"https://pith.science/pith/SNSR26KB2TAKQYDMDQXS4IWLMK","download_json":"https://pith.science/pith/SNSR26KB2TAKQYDMDQXS4IWLMK.json","view_paper":"https://pith.science/paper/SNSR26KB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06025&json=true","fetch_graph":"https://pith.science/api/pith-number/SNSR26KB2TAKQYDMDQXS4IWLMK/graph.json","fetch_events":"https://pith.science/api/pith-number/SNSR26KB2TAKQYDMDQXS4IWLMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNSR26KB2TAKQYDMDQXS4IWLMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNSR26KB2TAKQYDMDQXS4IWLMK/action/storage_attestation","attest_author":"https://pith.science/pith/SNSR26KB2TAKQYDMDQXS4IWLMK/action/author_attestation","sign_citation":"https://pith.science/pith/SNSR26KB2TAKQYDMDQXS4IWLMK/action/citation_signature","submit_replication":"https://pith.science/pith/SNSR26KB2TAKQYDMDQXS4IWLMK/action/replication_record"}},"created_at":"2026-07-05T07:07:08.823854+00:00","updated_at":"2026-07-05T07:07:08.823854+00:00"}