{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YCHF54GB4TB2X5AT2N5WFO4WU6","short_pith_number":"pith:YCHF54GB","schema_version":"1.0","canonical_sha256":"c08e5ef0c1e4c3abf413d37b62bb96a7aadc4f970ed6ab509c67272f7eed2a16","source":{"kind":"arxiv","id":"2306.08645","version":2},"attestation_state":"computed","paper":{"title":"Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bin Li, Xiangyang Xue, Xuli Shen, Zhiyu Jin","submitted_at":"2023-06-14T17:23:07Z","abstract_excerpt":"Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and evaluated on the images with fixed sizes. However, users are demanding for various images with specific sizes and various aspect ratio. This paper focuses on adapting text-to-image diffusion models to handle such variety while maintaining visual fidelity. First we observe that, during the synthesis, lower resolution images suffer from incomplete object portrayal, while higher resolution images exhibit repetitively dis"},"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":"2306.08645","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-14T17:23:07Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"8458542ac33f2c5bf071c5aff41a69060b30e06c4cae6edfea2ae3192afd520e","abstract_canon_sha256":"3bfddbbdf68ea99e055a3f5096ed99b3be892f76e03d9b68d12d237a731cf19e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:10.025389Z","signature_b64":"sNnUUZci8JlMP74X7SrJMmKoBe7MkB0RCpn2xp47K7quvuUxAEa1IUW9/r0LUHTJ4A2cqZvrsc2IyzSzdJU6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c08e5ef0c1e4c3abf413d37b62bb96a7aadc4f970ed6ab509c67272f7eed2a16","last_reissued_at":"2026-07-05T07:05:10.024920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:10.024920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bin Li, Xiangyang Xue, Xuli Shen, Zhiyu Jin","submitted_at":"2023-06-14T17:23:07Z","abstract_excerpt":"Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and evaluated on the images with fixed sizes. However, users are demanding for various images with specific sizes and various aspect ratio. This paper focuses on adapting text-to-image diffusion models to handle such variety while maintaining visual fidelity. First we observe that, during the synthesis, lower resolution images suffer from incomplete object portrayal, while higher resolution images exhibit repetitively dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08645","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/2306.08645/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":"2306.08645","created_at":"2026-07-05T07:05:10.024975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08645v2","created_at":"2026-07-05T07:05:10.024975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08645","created_at":"2026-07-05T07:05:10.024975+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCHF54GB4TB2","created_at":"2026-07-05T07:05:10.024975+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCHF54GB4TB2X5AT","created_at":"2026-07-05T07:05:10.024975+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCHF54GB","created_at":"2026-07-05T07:05:10.024975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07785","citing_title":"Pippo: High-Resolution Multi-View Humans from a Single Image","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCHF54GB4TB2X5AT2N5WFO4WU6","json":"https://pith.science/pith/YCHF54GB4TB2X5AT2N5WFO4WU6.json","graph_json":"https://pith.science/api/pith-number/YCHF54GB4TB2X5AT2N5WFO4WU6/graph.json","events_json":"https://pith.science/api/pith-number/YCHF54GB4TB2X5AT2N5WFO4WU6/events.json","paper":"https://pith.science/paper/YCHF54GB"},"agent_actions":{"view_html":"https://pith.science/pith/YCHF54GB4TB2X5AT2N5WFO4WU6","download_json":"https://pith.science/pith/YCHF54GB4TB2X5AT2N5WFO4WU6.json","view_paper":"https://pith.science/paper/YCHF54GB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08645&json=true","fetch_graph":"https://pith.science/api/pith-number/YCHF54GB4TB2X5AT2N5WFO4WU6/graph.json","fetch_events":"https://pith.science/api/pith-number/YCHF54GB4TB2X5AT2N5WFO4WU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCHF54GB4TB2X5AT2N5WFO4WU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCHF54GB4TB2X5AT2N5WFO4WU6/action/storage_attestation","attest_author":"https://pith.science/pith/YCHF54GB4TB2X5AT2N5WFO4WU6/action/author_attestation","sign_citation":"https://pith.science/pith/YCHF54GB4TB2X5AT2N5WFO4WU6/action/citation_signature","submit_replication":"https://pith.science/pith/YCHF54GB4TB2X5AT2N5WFO4WU6/action/replication_record"}},"created_at":"2026-07-05T07:05:10.024975+00:00","updated_at":"2026-07-05T07:05:10.024975+00:00"}