{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q63CBKUGOFF3IKEORAPR6KRYAB","short_pith_number":"pith:Q63CBKUG","schema_version":"1.0","canonical_sha256":"87b620aa86714bb4288e881f1f2a380055d39a8a510f03a02d8a800fafa3bc34","source":{"kind":"arxiv","id":"2210.12965","version":1},"attestation_state":"computed","paper":{"title":"High-Resolution Image Editing via Multi-Stage Blended Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Johannes Ackermann, Minjun Li","submitted_at":"2022-10-24T06:07:35Z","abstract_excerpt":"Diffusion models have shown great results in image generation and in image editing. However, current approaches are limited to low resolutions due to the computational cost of training diffusion models for high-resolution generation. We propose an approach that uses a pre-trained low-resolution diffusion model to edit images in the megapixel range. We first use Blended Diffusion to edit the image at a low resolution, and then upscale it in multiple stages, using a super-resolution model and Blended Diffusion. Using our approach, we achieve higher visual fidelity than by only applying off the s"},"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":"2210.12965","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-24T06:07:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b51b3925955ac34b653a5986ee01ff02c896b0051a1b8b4e3f374314e3a050d","abstract_canon_sha256":"92f17c2b26a3473eeccd401a9694ce931fb1c2bb4743760901501fc04ab44f81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:34.794905Z","signature_b64":"b6PsTnUuFo9LY7slek2AlFsSU3m+usu8WudER8ZIhLkLDBhQrHnEXNmYctpIPXEuGbedOvYUp/SMqkEmrY5NAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87b620aa86714bb4288e881f1f2a380055d39a8a510f03a02d8a800fafa3bc34","last_reissued_at":"2026-07-05T05:09:34.794556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:34.794556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Resolution Image Editing via Multi-Stage Blended Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Johannes Ackermann, Minjun Li","submitted_at":"2022-10-24T06:07:35Z","abstract_excerpt":"Diffusion models have shown great results in image generation and in image editing. However, current approaches are limited to low resolutions due to the computational cost of training diffusion models for high-resolution generation. We propose an approach that uses a pre-trained low-resolution diffusion model to edit images in the megapixel range. We first use Blended Diffusion to edit the image at a low resolution, and then upscale it in multiple stages, using a super-resolution model and Blended Diffusion. Using our approach, we achieve higher visual fidelity than by only applying off the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12965","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/2210.12965/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":"2210.12965","created_at":"2026-07-05T05:09:34.794617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12965v1","created_at":"2026-07-05T05:09:34.794617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12965","created_at":"2026-07-05T05:09:34.794617+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q63CBKUGOFF3","created_at":"2026-07-05T05:09:34.794617+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q63CBKUGOFF3IKEO","created_at":"2026-07-05T05:09:34.794617+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q63CBKUG","created_at":"2026-07-05T05:09:34.794617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06136","citing_title":"Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q63CBKUGOFF3IKEORAPR6KRYAB","json":"https://pith.science/pith/Q63CBKUGOFF3IKEORAPR6KRYAB.json","graph_json":"https://pith.science/api/pith-number/Q63CBKUGOFF3IKEORAPR6KRYAB/graph.json","events_json":"https://pith.science/api/pith-number/Q63CBKUGOFF3IKEORAPR6KRYAB/events.json","paper":"https://pith.science/paper/Q63CBKUG"},"agent_actions":{"view_html":"https://pith.science/pith/Q63CBKUGOFF3IKEORAPR6KRYAB","download_json":"https://pith.science/pith/Q63CBKUGOFF3IKEORAPR6KRYAB.json","view_paper":"https://pith.science/paper/Q63CBKUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12965&json=true","fetch_graph":"https://pith.science/api/pith-number/Q63CBKUGOFF3IKEORAPR6KRYAB/graph.json","fetch_events":"https://pith.science/api/pith-number/Q63CBKUGOFF3IKEORAPR6KRYAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q63CBKUGOFF3IKEORAPR6KRYAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q63CBKUGOFF3IKEORAPR6KRYAB/action/storage_attestation","attest_author":"https://pith.science/pith/Q63CBKUGOFF3IKEORAPR6KRYAB/action/author_attestation","sign_citation":"https://pith.science/pith/Q63CBKUGOFF3IKEORAPR6KRYAB/action/citation_signature","submit_replication":"https://pith.science/pith/Q63CBKUGOFF3IKEORAPR6KRYAB/action/replication_record"}},"created_at":"2026-07-05T05:09:34.794617+00:00","updated_at":"2026-07-05T05:09:34.794617+00:00"}