{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BYQODXMVCT2HLM4IORPSEQ2YC4","short_pith_number":"pith:BYQODXMV","schema_version":"1.0","canonical_sha256":"0e20e1dd9514f475b388745f2243581701aca316c0522d15b1eff6519916dbdc","source":{"kind":"arxiv","id":"2204.08583","version":2},"attestation_state":"computed","paper":{"title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Kornis, Dashiell Stander, Edward Raff, Eric Hallahan, Katherine Crowson, Louis Castricato, Stella Biderman","submitted_at":"2022-04-18T22:57:29Z","abstract_excerpt":"Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models. We demonstrate a novel methodology for both tasks which is capable of producing images of high visual quality from text prompts of significant semantic complexity without any training by using a multimodal encoder to guide image generations. We demonstrate on a variety of tasks how using CLIP [37] to guide VQGAN [11] produces higher visual quality outputs than prior, less flexible approaches like DALL-E [38], GLIDE [33] and Open-Edit [24], despi"},"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":"2204.08583","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T22:57:29Z","cross_cats_sorted":[],"title_canon_sha256":"0626aec27348c342fe14400f64a2dec9414d24a4080c6586864d6ea6b32f78d5","abstract_canon_sha256":"d35e9564e830ef3e213f000fb95ce04e22b490e465dd8224c6083fe5144255a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:19.933805Z","signature_b64":"/EBcYzNEn8duGk+xs4j+76IlPNuYhVBGm0qRM/usamachfo312zS35F2RUPZoqH4qnaSCzNPI10m0o+xJyYaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e20e1dd9514f475b388745f2243581701aca316c0522d15b1eff6519916dbdc","last_reissued_at":"2026-07-05T04:54:19.933386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:19.933386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Kornis, Dashiell Stander, Edward Raff, Eric Hallahan, Katherine Crowson, Louis Castricato, Stella Biderman","submitted_at":"2022-04-18T22:57:29Z","abstract_excerpt":"Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models. We demonstrate a novel methodology for both tasks which is capable of producing images of high visual quality from text prompts of significant semantic complexity without any training by using a multimodal encoder to guide image generations. We demonstrate on a variety of tasks how using CLIP [37] to guide VQGAN [11] produces higher visual quality outputs than prior, less flexible approaches like DALL-E [38], GLIDE [33] and Open-Edit [24], despi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08583","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/2204.08583/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":"2204.08583","created_at":"2026-07-05T04:54:19.933441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08583v2","created_at":"2026-07-05T04:54:19.933441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08583","created_at":"2026-07-05T04:54:19.933441+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYQODXMVCT2H","created_at":"2026-07-05T04:54:19.933441+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYQODXMVCT2HLM4I","created_at":"2026-07-05T04:54:19.933441+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYQODXMV","created_at":"2026-07-05T04:54:19.933441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30940","citing_title":"Motion Planning in Compressed Representation Spaces","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2404.10141","citing_title":"ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21116","citing_title":"GeoDiff-SAR II: 3D-Driven Foundation Diffusion Models for SAR Generation via Decoupled Control","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2304.01373","citing_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2205.11487","citing_title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2208.01618","citing_title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2208.01626","citing_title":"Prompt-to-Prompt Image Editing with Cross Attention Control","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYQODXMVCT2HLM4IORPSEQ2YC4","json":"https://pith.science/pith/BYQODXMVCT2HLM4IORPSEQ2YC4.json","graph_json":"https://pith.science/api/pith-number/BYQODXMVCT2HLM4IORPSEQ2YC4/graph.json","events_json":"https://pith.science/api/pith-number/BYQODXMVCT2HLM4IORPSEQ2YC4/events.json","paper":"https://pith.science/paper/BYQODXMV"},"agent_actions":{"view_html":"https://pith.science/pith/BYQODXMVCT2HLM4IORPSEQ2YC4","download_json":"https://pith.science/pith/BYQODXMVCT2HLM4IORPSEQ2YC4.json","view_paper":"https://pith.science/paper/BYQODXMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08583&json=true","fetch_graph":"https://pith.science/api/pith-number/BYQODXMVCT2HLM4IORPSEQ2YC4/graph.json","fetch_events":"https://pith.science/api/pith-number/BYQODXMVCT2HLM4IORPSEQ2YC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYQODXMVCT2HLM4IORPSEQ2YC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYQODXMVCT2HLM4IORPSEQ2YC4/action/storage_attestation","attest_author":"https://pith.science/pith/BYQODXMVCT2HLM4IORPSEQ2YC4/action/author_attestation","sign_citation":"https://pith.science/pith/BYQODXMVCT2HLM4IORPSEQ2YC4/action/citation_signature","submit_replication":"https://pith.science/pith/BYQODXMVCT2HLM4IORPSEQ2YC4/action/replication_record"}},"created_at":"2026-07-05T04:54:19.933441+00:00","updated_at":"2026-07-05T04:54:19.933441+00:00"}