{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V2JSTAMLBALLYPALMO2URKFQ5M","short_pith_number":"pith:V2JSTAML","schema_version":"1.0","canonical_sha256":"ae9329818b0816bc3c0b63b548a8b0eb273d26a143f604b27a7d71e30c8c68e3","source":{"kind":"arxiv","id":"2304.08818","version":2},"attestation_state":"computed","paper":{"title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andreas Blattmann, Huan Ling, Karsten Kreis, Robin Rombach, Sanja Fidler, Seung Wook Kim, Tim Dockhorn","submitted_at":"2023-04-18T08:30:32Z","abstract_excerpt":"Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution video generation, a particularly resource-intensive task. We first pre-train an LDM on images only; then, we turn the image generator into a video generator by introducing a temporal dimension to the latent space diffusion model and fine-tuning on encoded image sequences, i.e., videos. Similarly, we temporally align diffusion model upsamplers, turning them into"},"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":"2304.08818","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-18T08:30:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df3639b36ebbef659bb0cab7706e4e30fb301bb0ff843fbf4bc4363d34e319f0","abstract_canon_sha256":"4c834c88476f5f1865a6de8bdc57022e160a6387472431c2308d83d161c6935e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:27.907679Z","signature_b64":"UtrKpTUQ1cXBDsYiOnNz5lD/qgVL8MoD+luIXFld9F0peTy9Iu2ZoBSFsHa21bYB1zOIPos/btkTN+eFKlY+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae9329818b0816bc3c0b63b548a8b0eb273d26a143f604b27a7d71e30c8c68e3","last_reissued_at":"2026-07-05T07:28:27.907238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:27.907238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andreas Blattmann, Huan Ling, Karsten Kreis, Robin Rombach, Sanja Fidler, Seung Wook Kim, Tim Dockhorn","submitted_at":"2023-04-18T08:30:32Z","abstract_excerpt":"Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution video generation, a particularly resource-intensive task. We first pre-train an LDM on images only; then, we turn the image generator into a video generator by introducing a temporal dimension to the latent space diffusion model and fine-tuning on encoded image sequences, i.e., videos. Similarly, we temporally align diffusion model upsamplers, turning them into"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08818","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/2304.08818/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":"2304.08818","created_at":"2026-07-05T07:28:27.907290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08818v2","created_at":"2026-07-05T07:28:27.907290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08818","created_at":"2026-07-05T07:28:27.907290+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2JSTAMLBALL","created_at":"2026-07-05T07:28:27.907290+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2JSTAMLBALLYPAL","created_at":"2026-07-05T07:28:27.907290+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2JSTAML","created_at":"2026-07-05T07:28:27.907290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25550","citing_title":"DisagFusion: Asynchronous Pipeline Parallelism and Elastic Scheduling for Disaggregated Diffusion Serving","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07568","citing_title":"A Systematic Study of Behavioral Cloning for Scientific Data Annotation","ref_index":265,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08674","citing_title":"BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2408.14837","citing_title":"Diffusion Models Are Real-Time Game Engines","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06356","citing_title":"SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06356","citing_title":"SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2311.15127","citing_title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2307.01952","citing_title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2JSTAMLBALLYPALMO2URKFQ5M","json":"https://pith.science/pith/V2JSTAMLBALLYPALMO2URKFQ5M.json","graph_json":"https://pith.science/api/pith-number/V2JSTAMLBALLYPALMO2URKFQ5M/graph.json","events_json":"https://pith.science/api/pith-number/V2JSTAMLBALLYPALMO2URKFQ5M/events.json","paper":"https://pith.science/paper/V2JSTAML"},"agent_actions":{"view_html":"https://pith.science/pith/V2JSTAMLBALLYPALMO2URKFQ5M","download_json":"https://pith.science/pith/V2JSTAMLBALLYPALMO2URKFQ5M.json","view_paper":"https://pith.science/paper/V2JSTAML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08818&json=true","fetch_graph":"https://pith.science/api/pith-number/V2JSTAMLBALLYPALMO2URKFQ5M/graph.json","fetch_events":"https://pith.science/api/pith-number/V2JSTAMLBALLYPALMO2URKFQ5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2JSTAMLBALLYPALMO2URKFQ5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2JSTAMLBALLYPALMO2URKFQ5M/action/storage_attestation","attest_author":"https://pith.science/pith/V2JSTAMLBALLYPALMO2URKFQ5M/action/author_attestation","sign_citation":"https://pith.science/pith/V2JSTAMLBALLYPALMO2URKFQ5M/action/citation_signature","submit_replication":"https://pith.science/pith/V2JSTAMLBALLYPALMO2URKFQ5M/action/replication_record"}},"created_at":"2026-07-05T07:28:27.907290+00:00","updated_at":"2026-07-05T07:28:27.907290+00:00"}