{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4KMDQKB427VYKSG37IWTQUD5JH","short_pith_number":"pith:4KMDQKB4","schema_version":"1.0","canonical_sha256":"e29838283cd7eb8548dbfa2d38507d49ebe027a3232d1699b25eef70c021bc23","source":{"kind":"arxiv","id":"2407.02158","version":2},"attestation_state":"computed","paper":{"title":"UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Shao, Fenglong Song, Haoyu Chen, Jingjing Ren, Lei Zhu, Long Peng, Renjing Pei, Wenbo Li, Yong Guo","submitted_at":"2024-07-02T11:02:19Z","abstract_excerpt":"Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands. We present UltraPixel, a novel architecture utilizing cascade diffusion models to generate high-quality images at multiple resolutions (\\textit{e.g.}, 1K to 6K) within a single model, while maintaining computational efficiency. UltraPixel leverages semantics-rich representations of lower-resolution images in the later denoising stage to guide the whole generation of highly detailed high-resolution image"},"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":"2407.02158","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T11:02:19Z","cross_cats_sorted":[],"title_canon_sha256":"2df2a25eea6e8b7aff4a2ac1874a4b2b07eb485d55bfb8502a0a9568a8724d2b","abstract_canon_sha256":"bb5babd991beebc6fc0a0fa66b3f6029cbfa45c0ad96c48b630e91d0b976845e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:19.897544Z","signature_b64":"zvlgZqVE6v6ZYAEF6bzs9Z2sq+CAQiLWB0y4TKViV+9w/2cw9eXSOUpeBTdkAIIx11eJ3Tg3X8KUHbv9WRudDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e29838283cd7eb8548dbfa2d38507d49ebe027a3232d1699b25eef70c021bc23","last_reissued_at":"2026-07-05T08:40:19.896951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:19.896951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Shao, Fenglong Song, Haoyu Chen, Jingjing Ren, Lei Zhu, Long Peng, Renjing Pei, Wenbo Li, Yong Guo","submitted_at":"2024-07-02T11:02:19Z","abstract_excerpt":"Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands. We present UltraPixel, a novel architecture utilizing cascade diffusion models to generate high-quality images at multiple resolutions (\\textit{e.g.}, 1K to 6K) within a single model, while maintaining computational efficiency. UltraPixel leverages semantics-rich representations of lower-resolution images in the later denoising stage to guide the whole generation of highly detailed high-resolution image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02158","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/2407.02158/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":"2407.02158","created_at":"2026-07-05T08:40:19.897021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02158v2","created_at":"2026-07-05T08:40:19.897021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02158","created_at":"2026-07-05T08:40:19.897021+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KMDQKB427VY","created_at":"2026-07-05T08:40:19.897021+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KMDQKB427VYKSG3","created_at":"2026-07-05T08:40:19.897021+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KMDQKB4","created_at":"2026-07-05T08:40:19.897021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09150","citing_title":"Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2503.02537","citing_title":"RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21002","citing_title":"SURF: Signature-Retained Fast Video Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15684","citing_title":"ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2410.10629","citing_title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KMDQKB427VYKSG37IWTQUD5JH","json":"https://pith.science/pith/4KMDQKB427VYKSG37IWTQUD5JH.json","graph_json":"https://pith.science/api/pith-number/4KMDQKB427VYKSG37IWTQUD5JH/graph.json","events_json":"https://pith.science/api/pith-number/4KMDQKB427VYKSG37IWTQUD5JH/events.json","paper":"https://pith.science/paper/4KMDQKB4"},"agent_actions":{"view_html":"https://pith.science/pith/4KMDQKB427VYKSG37IWTQUD5JH","download_json":"https://pith.science/pith/4KMDQKB427VYKSG37IWTQUD5JH.json","view_paper":"https://pith.science/paper/4KMDQKB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02158&json=true","fetch_graph":"https://pith.science/api/pith-number/4KMDQKB427VYKSG37IWTQUD5JH/graph.json","fetch_events":"https://pith.science/api/pith-number/4KMDQKB427VYKSG37IWTQUD5JH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KMDQKB427VYKSG37IWTQUD5JH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KMDQKB427VYKSG37IWTQUD5JH/action/storage_attestation","attest_author":"https://pith.science/pith/4KMDQKB427VYKSG37IWTQUD5JH/action/author_attestation","sign_citation":"https://pith.science/pith/4KMDQKB427VYKSG37IWTQUD5JH/action/citation_signature","submit_replication":"https://pith.science/pith/4KMDQKB427VYKSG37IWTQUD5JH/action/replication_record"}},"created_at":"2026-07-05T08:40:19.897021+00:00","updated_at":"2026-07-05T08:40:19.897021+00:00"}