{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FAIAUE5U2IK4OMGENZQ7Z7HFIZ","short_pith_number":"pith:FAIAUE5U","schema_version":"1.0","canonical_sha256":"28100a13b4d215c730c46e61fcfce5465ab168d9a33917d321bc3804539769dc","source":{"kind":"arxiv","id":"2211.12572","version":1},"attestation_state":"computed","paper":{"title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Michal Geyer, Narek Tumanyan, Shai Bagon, Tali Dekel","submitted_at":"2022-11-22T20:39:18Z","abstract_excerpt":"Large-scale text-to-image generative models have been a revolutionary breakthrough in the evolution of generative AI, allowing us to synthesize diverse images that convey highly complex visual concepts. However, a pivotal challenge in leveraging such models for real-world content creation tasks is providing users with control over the generated content. In this paper, we present a new framework that takes text-to-image synthesis to the realm of image-to-image translation -- given a guidance image and a target text prompt, our method harnesses the power of a pre-trained text-to-image diffusion "},"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":"2211.12572","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T20:39:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e728943b7f60580a26e95cb719a6cd84737996e8aa4571040a0bbc1edc118f77","abstract_canon_sha256":"bbc4a64fdc4d9a7ae6817cb73df1bd42bb10401e35800df0aefc3b905944b6bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:52.425940Z","signature_b64":"GSp9gbNFPfcgwu9QcoGB8Ry63yBZ6S+TfS2nHeqTR9N+7sHejZ4k7w+8aoRQXDrNJdSojF7tLcj8eqO0jeGODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28100a13b4d215c730c46e61fcfce5465ab168d9a33917d321bc3804539769dc","last_reissued_at":"2026-07-05T05:18:52.425514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:52.425514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Michal Geyer, Narek Tumanyan, Shai Bagon, Tali Dekel","submitted_at":"2022-11-22T20:39:18Z","abstract_excerpt":"Large-scale text-to-image generative models have been a revolutionary breakthrough in the evolution of generative AI, allowing us to synthesize diverse images that convey highly complex visual concepts. However, a pivotal challenge in leveraging such models for real-world content creation tasks is providing users with control over the generated content. In this paper, we present a new framework that takes text-to-image synthesis to the realm of image-to-image translation -- given a guidance image and a target text prompt, our method harnesses the power of a pre-trained text-to-image diffusion "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12572","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/2211.12572/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":"2211.12572","created_at":"2026-07-05T05:18:52.425571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12572v1","created_at":"2026-07-05T05:18:52.425571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12572","created_at":"2026-07-05T05:18:52.425571+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAIAUE5U2IK4","created_at":"2026-07-05T05:18:52.425571+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAIAUE5U2IK4OMGE","created_at":"2026-07-05T05:18:52.425571+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAIAUE5U","created_at":"2026-07-05T05:18:52.425571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23682","citing_title":"Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07117","citing_title":"Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2405.18716","citing_title":"SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05342","citing_title":"Delta Rectified Flow Sampling for Text-to-Image Editing","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2302.05543","citing_title":"Adding Conditional Control to Text-to-Image Diffusion Models","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23540","citing_title":"Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00707","citing_title":"PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02583","citing_title":"Stylistic Attribute Control in Latent Diffusion Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02583","citing_title":"Stylistic Attribute Control in Latent Diffusion Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAIAUE5U2IK4OMGENZQ7Z7HFIZ","json":"https://pith.science/pith/FAIAUE5U2IK4OMGENZQ7Z7HFIZ.json","graph_json":"https://pith.science/api/pith-number/FAIAUE5U2IK4OMGENZQ7Z7HFIZ/graph.json","events_json":"https://pith.science/api/pith-number/FAIAUE5U2IK4OMGENZQ7Z7HFIZ/events.json","paper":"https://pith.science/paper/FAIAUE5U"},"agent_actions":{"view_html":"https://pith.science/pith/FAIAUE5U2IK4OMGENZQ7Z7HFIZ","download_json":"https://pith.science/pith/FAIAUE5U2IK4OMGENZQ7Z7HFIZ.json","view_paper":"https://pith.science/paper/FAIAUE5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12572&json=true","fetch_graph":"https://pith.science/api/pith-number/FAIAUE5U2IK4OMGENZQ7Z7HFIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FAIAUE5U2IK4OMGENZQ7Z7HFIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAIAUE5U2IK4OMGENZQ7Z7HFIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAIAUE5U2IK4OMGENZQ7Z7HFIZ/action/storage_attestation","attest_author":"https://pith.science/pith/FAIAUE5U2IK4OMGENZQ7Z7HFIZ/action/author_attestation","sign_citation":"https://pith.science/pith/FAIAUE5U2IK4OMGENZQ7Z7HFIZ/action/citation_signature","submit_replication":"https://pith.science/pith/FAIAUE5U2IK4OMGENZQ7Z7HFIZ/action/replication_record"}},"created_at":"2026-07-05T05:18:52.425571+00:00","updated_at":"2026-07-05T05:18:52.425571+00:00"}