{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q5RBWHPZIOTHZ7KKW4VQISZDWS","short_pith_number":"pith:Q5RBWHPZ","schema_version":"1.0","canonical_sha256":"87621b1df943a67cfd4ab72b044b23b487c1fd4eb047504a939368a0f006d67e","source":{"kind":"arxiv","id":"2310.07702","version":1},"attestation_state":"computed","paper":{"title":"ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxin Chen, Menghan Xia, Qifeng Chen, Ran He, Shaoshu Yang, Xiaodong Cun, Xintao Wang, Yingqing He, Ying Shan, Yong Zhang","submitted_at":"2023-10-11T17:52:39Z","abstract_excerpt":"In this work, we investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes. In addition, the generated images should have arbitrary image aspect ratios. When generating images directly at a higher resolution, 1024 x 1024, with the pre-trained Stable Diffusion using training images of resolution 512 x 512, we observe persistent problems of object repetition and unreasonable object structures. Existing works for higher-resolution generation, such as attention-based and joint-diffusion approaches, cannot well address"},"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":"2310.07702","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:52:39Z","cross_cats_sorted":[],"title_canon_sha256":"38adaea8bb067b8ca5fa2d7c5480149ae6fc5234d4c08c38a4e4355abd6c7113","abstract_canon_sha256":"b20938997d0a2b8b902c9ae9f01c9dc8618895022b562fa9cadb4efe7e7d9378"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:48.722663Z","signature_b64":"SM2V5Pnq60heLsBC+rxW4u35tWuji4Ta9KMejA/H03O5oLwvkqJVTqb4TrVRb0l1o3P4U8AwLfz5yIL7ne3qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87621b1df943a67cfd4ab72b044b23b487c1fd4eb047504a939368a0f006d67e","last_reissued_at":"2026-07-05T06:59:48.722170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:48.722170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxin Chen, Menghan Xia, Qifeng Chen, Ran He, Shaoshu Yang, Xiaodong Cun, Xintao Wang, Yingqing He, Ying Shan, Yong Zhang","submitted_at":"2023-10-11T17:52:39Z","abstract_excerpt":"In this work, we investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes. In addition, the generated images should have arbitrary image aspect ratios. When generating images directly at a higher resolution, 1024 x 1024, with the pre-trained Stable Diffusion using training images of resolution 512 x 512, we observe persistent problems of object repetition and unreasonable object structures. Existing works for higher-resolution generation, such as attention-based and joint-diffusion approaches, cannot well address"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07702","kind":"arxiv","version":1},"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/2310.07702/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":"2310.07702","created_at":"2026-07-05T06:59:48.722228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07702v1","created_at":"2026-07-05T06:59:48.722228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07702","created_at":"2026-07-05T06:59:48.722228+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5RBWHPZIOTH","created_at":"2026-07-05T06:59:48.722228+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5RBWHPZIOTHZ7KK","created_at":"2026-07-05T06:59:48.722228+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5RBWHPZ","created_at":"2026-07-05T06:59:48.722228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2310.19512","citing_title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5RBWHPZIOTHZ7KKW4VQISZDWS","json":"https://pith.science/pith/Q5RBWHPZIOTHZ7KKW4VQISZDWS.json","graph_json":"https://pith.science/api/pith-number/Q5RBWHPZIOTHZ7KKW4VQISZDWS/graph.json","events_json":"https://pith.science/api/pith-number/Q5RBWHPZIOTHZ7KKW4VQISZDWS/events.json","paper":"https://pith.science/paper/Q5RBWHPZ"},"agent_actions":{"view_html":"https://pith.science/pith/Q5RBWHPZIOTHZ7KKW4VQISZDWS","download_json":"https://pith.science/pith/Q5RBWHPZIOTHZ7KKW4VQISZDWS.json","view_paper":"https://pith.science/paper/Q5RBWHPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07702&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5RBWHPZIOTHZ7KKW4VQISZDWS/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5RBWHPZIOTHZ7KKW4VQISZDWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5RBWHPZIOTHZ7KKW4VQISZDWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5RBWHPZIOTHZ7KKW4VQISZDWS/action/storage_attestation","attest_author":"https://pith.science/pith/Q5RBWHPZIOTHZ7KKW4VQISZDWS/action/author_attestation","sign_citation":"https://pith.science/pith/Q5RBWHPZIOTHZ7KKW4VQISZDWS/action/citation_signature","submit_replication":"https://pith.science/pith/Q5RBWHPZIOTHZ7KKW4VQISZDWS/action/replication_record"}},"created_at":"2026-07-05T06:59:48.722228+00:00","updated_at":"2026-07-05T06:59:48.722228+00:00"}