{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G5YGYN72N7IYUO6JCLQIS6C7D2","short_pith_number":"pith:G5YGYN72","schema_version":"1.0","canonical_sha256":"37706c37fa6fd18a3bc912e089785f1e8be4b638027b2ce7c17747a70ab8a2a7","source":{"kind":"arxiv","id":"2310.12190","version":2},"attestation_state":"computed","paper":{"title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanyuan Liu, Haoxin Chen, Jinbo Xing, Menghan Xia, Tien-Tsin Wong, Wangbo Yu, Xintao Wang, Ying Shan, Yong Zhang","submitted_at":"2023-10-18T14:42:16Z","abstract_excerpt":"Animating a still image offers an engaging visual experience. Traditional image animation techniques mainly focus on animating natural scenes with stochastic dynamics (e.g. clouds and fluid) or domain-specific motions (e.g. human hair or body motions), and thus limits their applicability to more general visual content. To overcome this limitation, we explore the synthesis of dynamic content for open-domain images, converting them into animated videos. The key idea is to utilize the motion prior of text-to-video diffusion models by incorporating the image into the generative process as guidance"},"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":"2310.12190","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-18T14:42:16Z","cross_cats_sorted":[],"title_canon_sha256":"900e9f5353d80436b96de50be239f9e79af988b3185b82885017dbabe0b981c3","abstract_canon_sha256":"86d7ac282d549e7bc933751dd078744a8970c786100ebf4518c0d63050e8bcd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:47.813626Z","signature_b64":"yaTGZoaW0yDptsqyZ8vZPhKP53vSND4H2qNZ6r92EgJ0R+p5Ei2a/AKFuq0vs8oLJNK52Zbl6Hy2xOyRAZFzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37706c37fa6fd18a3bc912e089785f1e8be4b638027b2ce7c17747a70ab8a2a7","last_reissued_at":"2026-07-05T07:16:47.813218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:47.813218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanyuan Liu, Haoxin Chen, Jinbo Xing, Menghan Xia, Tien-Tsin Wong, Wangbo Yu, Xintao Wang, Ying Shan, Yong Zhang","submitted_at":"2023-10-18T14:42:16Z","abstract_excerpt":"Animating a still image offers an engaging visual experience. Traditional image animation techniques mainly focus on animating natural scenes with stochastic dynamics (e.g. clouds and fluid) or domain-specific motions (e.g. human hair or body motions), and thus limits their applicability to more general visual content. To overcome this limitation, we explore the synthesis of dynamic content for open-domain images, converting them into animated videos. The key idea is to utilize the motion prior of text-to-video diffusion models by incorporating the image into the generative process as guidance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12190","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/2310.12190/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":"2310.12190","created_at":"2026-07-05T07:16:47.813273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12190v2","created_at":"2026-07-05T07:16:47.813273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12190","created_at":"2026-07-05T07:16:47.813273+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5YGYN72N7IY","created_at":"2026-07-05T07:16:47.813273+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5YGYN72N7IYUO6J","created_at":"2026-07-05T07:16:47.813273+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5YGYN72","created_at":"2026-07-05T07:16:47.813273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24107","citing_title":"DramaDirector: Geometry-Guided Short Drama Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2411.14295","citing_title":"DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21431","citing_title":"iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04145","citing_title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2502.06764","citing_title":"History-Guided Video Diffusion","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02048","citing_title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5YGYN72N7IYUO6JCLQIS6C7D2","json":"https://pith.science/pith/G5YGYN72N7IYUO6JCLQIS6C7D2.json","graph_json":"https://pith.science/api/pith-number/G5YGYN72N7IYUO6JCLQIS6C7D2/graph.json","events_json":"https://pith.science/api/pith-number/G5YGYN72N7IYUO6JCLQIS6C7D2/events.json","paper":"https://pith.science/paper/G5YGYN72"},"agent_actions":{"view_html":"https://pith.science/pith/G5YGYN72N7IYUO6JCLQIS6C7D2","download_json":"https://pith.science/pith/G5YGYN72N7IYUO6JCLQIS6C7D2.json","view_paper":"https://pith.science/paper/G5YGYN72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12190&json=true","fetch_graph":"https://pith.science/api/pith-number/G5YGYN72N7IYUO6JCLQIS6C7D2/graph.json","fetch_events":"https://pith.science/api/pith-number/G5YGYN72N7IYUO6JCLQIS6C7D2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5YGYN72N7IYUO6JCLQIS6C7D2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5YGYN72N7IYUO6JCLQIS6C7D2/action/storage_attestation","attest_author":"https://pith.science/pith/G5YGYN72N7IYUO6JCLQIS6C7D2/action/author_attestation","sign_citation":"https://pith.science/pith/G5YGYN72N7IYUO6JCLQIS6C7D2/action/citation_signature","submit_replication":"https://pith.science/pith/G5YGYN72N7IYUO6JCLQIS6C7D2/action/replication_record"}},"created_at":"2026-07-05T07:16:47.813273+00:00","updated_at":"2026-07-05T07:16:47.813273+00:00"}